Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5619 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.8879. Min Act: -0.1700
Data Index: 2672910 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.8254. Min Act: -0.1700
Data Index: 7889207 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.8254. Min Act: -0.1700
Data Index: 3647807 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.6691. Min Act: -0.1700
Data Index: 1395205 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.6379. Min Act: -0.1700
Data Index: 7835939 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.6066. Min Act: -0.1700
Data Index: 8551377 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.6066. Min Act: -0.1700
Data Index: 8653307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5754. Min Act: -0.1700
Data Index: 4861677 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5754. Min Act: -0.1700
Data Index: 5257821 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5754. Min Act: -0.1700
Data Index: 2164257 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5754. Min Act: -0.1700
Data Index: 7030452 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5754. Min Act: -0.1700
Data Index: 8085614 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5754. Min Act: -0.1700
Data Index: 7512870 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5441. Min Act: -0.1700
Data Index: 3861865 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5129. Min Act: -0.1700
Data Index: 1090090 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5441. Min Act: -0.1700
Data Index: 2146087 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5441. Min Act: -0.1700
Data Index: 4784617 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5441. Min Act: -0.1700
Data Index: 734794 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5441. Min Act: -0.1700
Data Index: 2642209 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8879. Min Range: -5.8879
Max Act: 5.5129. Min Act: -0.1700
Data Index: 2885290 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19