Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2582 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0152. Min Range: -7.0152
Max Act: 7.0152. Min Act: -0.1700
Data Index: 957055 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.9527. Min Act: -0.1700
Data Index: 135467 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.8277. Min Act: -0.1700
Data Index: 31514 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.6402. Min Act: -0.1700
Data Index: 7945866 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.6090. Min Act: -0.1700
Data Index: 5123855 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.5152. Min Act: -0.1700
Data Index: 1692478 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.4840. Min Act: -0.1700
Data Index: 7307954 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.5152. Min Act: -0.1700
Data Index: 7277820 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.4215. Min Act: -0.1700
Data Index: 3740808 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.4215. Min Act: -0.1700
Data Index: 5733597 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.4215. Min Act: -0.1700
Data Index: 4788225 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.4215. Min Act: -0.1700
Data Index: 4960610 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.4215. Min Act: -0.1700
Data Index: 6738965 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.3590. Min Act: -0.1700
Data Index: 5549446 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.4215. Min Act: -0.1700
Data Index: 73748 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.3902. Min Act: -0.1700
Data Index: 515354 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.4215. Min Act: -0.1700
Data Index: 4309910 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.4215. Min Act: -0.1700
Data Index: 6679594 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.4215. Min Act: -0.1700
Data Index: 6967380 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0152. Min Range: -7.0152
Max Act: 6.3590. Min Act: -0.1700
Data Index: 1069670 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19