Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2179 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.6135. Min Act: -0.1700
Data Index: 6449099 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.6135. Min Act: -0.1700
Data Index: 6129858 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.5510. Min Act: -0.1700
Data Index: 6794002 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.4260. Min Act: -0.1700
Data Index: 8417253 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.4885. Min Act: -0.1700
Data Index: 1900959 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.4260. Min Act: -0.1700
Data Index: 2566877 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.3635. Min Act: -0.1700
Data Index: 3094063 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.3635. Min Act: -0.1700
Data Index: 3578877 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.3635. Min Act: -0.1700
Data Index: 1745931 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.3010. Min Act: -0.1700
Data Index: 3947008 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.2385. Min Act: -0.1700
Data Index: 1330152 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.2385. Min Act: -0.1700
Data Index: 5878550 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.1760. Min Act: -0.1700
Data Index: 6845952 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.2385. Min Act: -0.1700
Data Index: 2566878 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.1760. Min Act: -0.1700
Data Index: 1322642 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.1760. Min Act: -0.1700
Data Index: 3386411 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.1760. Min Act: -0.1700
Data Index: 7200423 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.1135. Min Act: -0.1700
Data Index: 5740628 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.0510. Min Act: -0.1700
Data Index: 7698094 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6135. Min Range: -10.6135
Max Act: 10.0510. Min Act: -0.1700
Data Index: 589539 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19