Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.9454. Min Act: -0.1700
Data Index: 2061560 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.9141. Min Act: -0.1700
Data Index: 7579170 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.8204. Min Act: -0.1700
Data Index: 4567887 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.6329. Min Act: -0.1700
Data Index: 384185 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.6329. Min Act: -0.1700
Data Index: 843714 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.6016. Min Act: -0.1700
Data Index: 2425302 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.6016. Min Act: -0.1700
Data Index: 1293473 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5704. Min Act: -0.1700
Data Index: 4876125 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5391. Min Act: -0.1700
Data Index: 6333688 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5079. Min Act: -0.1700
Data Index: 5162886 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.5079. Min Act: -0.1700
Data Index: 3258322 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4766. Min Act: -0.1700
Data Index: 3624969 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4454. Min Act: -0.1700
Data Index: 5526727 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4141. Min Act: -0.1700
Data Index: 2697327 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4766. Min Act: -0.1700
Data Index: 5846755 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4454. Min Act: -0.1700
Data Index: 8056786 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4141. Min Act: -0.1700
Data Index: 577231 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4141. Min Act: -0.1700
Data Index: 5547727 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4141. Min Act: -0.1700
Data Index: 1867188 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9454. Min Range: -6.9454
Max Act: 6.4141. Min Act: -0.1700
Data Index: 2474345 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19