Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3327 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.5145. Min Act: -0.1700
Data Index: 7848186 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.4496. Min Act: -0.1700
Data Index: 1469930 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.4008. Min Act: -0.1700
Data Index: 7008825 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.4334. Min Act: -0.1700
Data Index: 3138301 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.4334. Min Act: -0.1700
Data Index: 5981907 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.4171. Min Act: -0.1700
Data Index: 4217617 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.4171. Min Act: -0.1700
Data Index: 873651 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3844. Min Act: -0.1700
Data Index: 7076507 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3681. Min Act: -0.1700
Data Index: 5359168 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3681. Min Act: -0.1700
Data Index: 2950824 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3681. Min Act: -0.1700
Data Index: 1059077 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3681. Min Act: -0.1700
Data Index: 6009903 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3681. Min Act: -0.1700
Data Index: 2525137 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3517. Min Act: -0.1700
Data Index: 6962701 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3517. Min Act: -0.1700
Data Index: 7668993 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3517. Min Act: -0.1700
Data Index: 8347202 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3517. Min Act: -0.1700
Data Index: 6315549 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3517. Min Act: -0.1700
Data Index: 3487703 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3517. Min Act: -0.1700
Data Index: 7261857 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5145. Min Range: -2.5145
Max Act: 2.3681. Min Act: -0.1700
Data Index: 2988447 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19