Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.6149. Min Act: -0.1700
Data Index: 5569400 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.4586. Min Act: -0.1700
Data Index: 5599755 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.3961. Min Act: -0.1700
Data Index: 7939721 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.3961. Min Act: -0.1700
Data Index: 2300817 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.3649. Min Act: -0.1700
Data Index: 7980537 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.3649. Min Act: -0.1700
Data Index: 7753131 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.2086. Min Act: -0.1700
Data Index: 3671095 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.1774. Min Act: -0.1700
Data Index: 6447859 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.1774. Min Act: -0.1700
Data Index: 6941806 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.1774. Min Act: -0.1700
Data Index: 5685736 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.1149. Min Act: -0.1700
Data Index: 7718449 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.1149. Min Act: -0.1700
Data Index: 1369467 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.1149. Min Act: -0.1700
Data Index: 5854170 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6149. Min Range: -6.6149
Max Act: 6.1149. Min Act: -0.1700
Data Index: 1781848 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6149. Min Range: -6.6149
Max Act: 5.9899. Min Act: -0.1700
Data Index: 8074282 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6149. Min Range: -6.6149
Max Act: 5.9899. Min Act: -0.1700
Data Index: 3328360 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6149. Min Range: -6.6149
Max Act: 5.9899. Min Act: -0.1700
Data Index: 1488391 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6149. Min Range: -6.6149
Max Act: 5.9899. Min Act: -0.1700
Data Index: 8081761 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6149. Min Range: -6.6149
Max Act: 5.9586. Min Act: -0.1700
Data Index: 823516 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6149. Min Range: -6.6149
Max Act: 5.9586. Min Act: -0.1700
Data Index: 5914099 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19