Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.4985. Min Act: -0.1700
Data Index: 1245497 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.4672. Min Act: -0.1700
Data Index: 2876769 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.4360. Min Act: -0.1700
Data Index: 4462129 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.4360. Min Act: -0.1700
Data Index: 2536317 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.3735. Min Act: -0.1700
Data Index: 6897012 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.2797. Min Act: -0.1700
Data Index: 7044285 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.2797. Min Act: -0.1700
Data Index: 7288086 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.2172. Min Act: -0.1700
Data Index: 2073483 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.1860. Min Act: -0.1700
Data Index: 6678931 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.1860. Min Act: -0.1700
Data Index: 3506418 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0922. Min Act: -0.1700
Data Index: 8222681 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.1235. Min Act: -0.1700
Data Index: 1703428 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.1235. Min Act: -0.1700
Data Index: 6162821 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0922. Min Act: -0.1700
Data Index: 7016341 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.1235. Min Act: -0.1700
Data Index: 655002 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0922. Min Act: -0.1700
Data Index: 3911985 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.1235. Min Act: -0.1700
Data Index: 3355218 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0610. Min Act: -0.1700
Data Index: 7055044 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0297. Min Act: -0.1700
Data Index: 3475585 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4985. Min Range: -6.4985
Max Act: 6.0297. Min Act: -0.1700
Data Index: 220498 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19