Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1356 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.9448. Min Act: -0.1700
Data Index: 5678627 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.8823. Min Act: -0.1700
Data Index: 8056598 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.8511. Min Act: -0.1700
Data Index: 7504327 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.8198. Min Act: -0.1700
Data Index: 3122503 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.7573. Min Act: -0.1700
Data Index: 304138 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.7886. Min Act: -0.1700
Data Index: 8637375 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.6323. Min Act: -0.1700
Data Index: 6454644 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.6323. Min Act: -0.1700
Data Index: 121360 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.6323. Min Act: -0.1700
Data Index: 2546892 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.6011. Min Act: -0.1700
Data Index: 4022085 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.6323. Min Act: -0.1700
Data Index: 1593829 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5698. Min Act: -0.1700
Data Index: 5348411 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5698. Min Act: -0.1700
Data Index: 7349801 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5386. Min Act: -0.1700
Data Index: 427412 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5698. Min Act: -0.1700
Data Index: 7763662 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5698. Min Act: -0.1700
Data Index: 8338263 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5386. Min Act: -0.1700
Data Index: 6580487 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5386. Min Act: -0.1700
Data Index: 671875 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5073. Min Act: -0.1700
Data Index: 1926837 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9448. Min Range: -6.9448
Max Act: 6.5073. Min Act: -0.1700
Data Index: 239944 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19