Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4132 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.4879. Min Act: -0.1700
Data Index: 8571136 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.3942. Min Act: -0.1700
Data Index: 8562493 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.3629. Min Act: -0.1700
Data Index: 6081352 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.3629. Min Act: -0.1700
Data Index: 1961269 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.2692. Min Act: -0.1700
Data Index: 2656532 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.2379. Min Act: -0.1700
Data Index: 8416239 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.1754. Min Act: -0.1700
Data Index: 8726847 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.2067. Min Act: -0.1700
Data Index: 2525122 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.1754. Min Act: -0.1700
Data Index: 36931 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.1129. Min Act: -0.1700
Data Index: 7929525 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.1129. Min Act: -0.1700
Data Index: 2918589 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.1129. Min Act: -0.1700
Data Index: 3041976 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.0504. Min Act: -0.1700
Data Index: 7716096 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.0504. Min Act: -0.1700
Data Index: 7380379 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.0504. Min Act: -0.1700
Data Index: 2808856 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.0504. Min Act: -0.1700
Data Index: 6753310 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.0192. Min Act: -0.1700
Data Index: 6545174 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.0192. Min Act: -0.1700
Data Index: 2109463 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.0192. Min Act: -0.1700
Data Index: 2352422 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4879. Min Range: -6.4879
Max Act: 6.0504. Min Act: -0.1700
Data Index: 2312686 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19