Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1809 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.5242. Min Act: -0.1700
Data Index: 845923 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.4929. Min Act: -0.1700
Data Index: 4410460 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.4304. Min Act: -0.1700
Data Index: 3276847 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.4304. Min Act: -0.1700
Data Index: 3907608 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3992. Min Act: -0.1700
Data Index: 8208233 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3679. Min Act: -0.1700
Data Index: 3788494 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3679. Min Act: -0.1700
Data Index: 4859993 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3679. Min Act: -0.1700
Data Index: 7780794 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3367. Min Act: -0.1700
Data Index: 3145226 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3367. Min Act: -0.1700
Data Index: 7286744 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3367. Min Act: -0.1700
Data Index: 181998 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3367. Min Act: -0.1700
Data Index: 1609828 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3367. Min Act: -0.1700
Data Index: 7989587 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3054. Min Act: -0.1700
Data Index: 6864744 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3054. Min Act: -0.1700
Data Index: 2176006 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3054. Min Act: -0.1700
Data Index: 5678093 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3054. Min Act: -0.1700
Data Index: 3433404 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3054. Min Act: -0.1700
Data Index: 6593889 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.3054. Min Act: -0.1700
Data Index: 4878637 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5242. Min Range: -5.5242
Max Act: 5.2742. Min Act: -0.1700
Data Index: 679371 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19