Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5389 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4939. Min Range: -10.4939
Max Act: 10.4939. Min Act: -0.1700
Data Index: 2358268 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4939. Min Range: -10.4939
Max Act: 10.0564. Min Act: -0.1700
Data Index: 1047212 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.8689. Min Act: -0.1700
Data Index: 1518257 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.7439. Min Act: -0.1700
Data Index: 5086848 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.7439. Min Act: -0.1700
Data Index: 5012647 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.6814. Min Act: -0.1700
Data Index: 7432669 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.6814. Min Act: -0.1700
Data Index: 4660545 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.6814. Min Act: -0.1700
Data Index: 7093119 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.6189. Min Act: -0.1700
Data Index: 390790 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.6189. Min Act: -0.1700
Data Index: 7273807 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.6189. Min Act: -0.1700
Data Index: 6256927 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.5564. Min Act: -0.1700
Data Index: 3972519 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.5564. Min Act: -0.1700
Data Index: 7734683 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.5564. Min Act: -0.1700
Data Index: 7489480 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.4939. Min Act: -0.1700
Data Index: 1946345 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.4939. Min Act: -0.1700
Data Index: 495652 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.4939. Min Act: -0.1700
Data Index: 6117420 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.5564. Min Act: -0.1700
Data Index: 955735 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.4314. Min Act: -0.1700
Data Index: 6366855 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4939. Min Range: -10.4939
Max Act: 9.4314. Min Act: -0.1700
Data Index: 1355781 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19