Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1848 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.3439. Min Range: -10.3439
Max Act: 10.3439. Min Act: -0.1700
Data Index: 1147408 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3439. Min Range: -10.3439
Max Act: 10.2189. Min Act: -0.1700
Data Index: 1147407 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3439. Min Range: -10.3439
Max Act: 10.0939. Min Act: -0.1700
Data Index: 4157144 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3439. Min Range: -10.3439
Max Act: 10.0314. Min Act: -0.1700
Data Index: 8300471 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3439. Min Range: -10.3439
Max Act: 10.0939. Min Act: -0.1700
Data Index: 3912742 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3439. Min Range: -10.3439
Max Act: 10.0314. Min Act: -0.1700
Data Index: 3635141 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.9064. Min Act: -0.1700
Data Index: 6499120 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.7814. Min Act: -0.1700
Data Index: 8736008 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.7814. Min Act: -0.1700
Data Index: 5932271 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.7814. Min Act: -0.1700
Data Index: 8208699 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.7814. Min Act: -0.1700
Data Index: 4238220 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.7189. Min Act: -0.1700
Data Index: 8826692 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.7189. Min Act: -0.1700
Data Index: 1142254 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.7189. Min Act: -0.1700
Data Index: 7224610 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.7189. Min Act: -0.1700
Data Index: 2713014 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.7189. Min Act: -0.1700
Data Index: 3284861 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.5939. Min Act: -0.1700
Data Index: 624604 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.5939. Min Act: -0.1700
Data Index: 1331369 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.5939. Min Act: -0.1700
Data Index: 5504882 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3439. Min Range: -10.3439
Max Act: 9.5939. Min Act: -0.1700
Data Index: 4006955 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19