Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 571 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.3565. Min Act: -0.1700
Data Index: 5725248 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.2628. Min Act: -0.1700
Data Index: 4212716 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.2003. Min Act: -0.1700
Data Index: 8483061 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.2315. Min Act: -0.1700
Data Index: 7226995 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.1378. Min Act: -0.1700
Data Index: 7703564 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.2003. Min Act: -0.1700
Data Index: 1138007 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.1378. Min Act: -0.1700
Data Index: 659995 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.1378. Min Act: -0.1700
Data Index: 4490514 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.1065. Min Act: -0.1700
Data Index: 4991936 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0753. Min Act: -0.1700
Data Index: 1791644 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0753. Min Act: -0.1700
Data Index: 8074419 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0440. Min Act: -0.1700
Data Index: 5528631 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0128. Min Act: -0.1700
Data Index: 5415623 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0128. Min Act: -0.1700
Data Index: 6771772 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.0128. Min Act: -0.1700
Data Index: 8471391 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9503. Min Act: -0.1700
Data Index: 5768027 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9503. Min Act: -0.1700
Data Index: 3420384 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.8878. Min Act: -0.1700
Data Index: 7884820 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9190. Min Act: -0.1700
Data Index: 1296472 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9190. Min Act: -0.1700
Data Index: 3002558 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19