Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 264 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.7313. Min Act: -0.1700
Data Index: 36844 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.5438. Min Act: -0.1700
Data Index: 2416081 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.5438. Min Act: -0.1700
Data Index: 8352770 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.4813. Min Act: -0.1700
Data Index: 1499773 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.4188. Min Act: -0.1700
Data Index: 1402664 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.3563. Min Act: -0.1700
Data Index: 1120180 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.3563. Min Act: -0.1700
Data Index: 3971494 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.3563. Min Act: -0.1700
Data Index: 4889838 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.2938. Min Act: -0.1700
Data Index: 3508598 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.3563. Min Act: -0.1700
Data Index: 4646160 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.2938. Min Act: -0.1700
Data Index: 8307591 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.2938. Min Act: -0.1700
Data Index: 3955054 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.2938. Min Act: -0.1700
Data Index: 7555387 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.2938. Min Act: -0.1700
Data Index: 1801702 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.2313. Min Act: -0.1700
Data Index: 5344436 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.2313. Min Act: -0.1700
Data Index: 1562474 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.1688. Min Act: -0.1700
Data Index: 1132985 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.1688. Min Act: -0.1700
Data Index: 6150150 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.1688. Min Act: -0.1700
Data Index: 6497187 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7313. Min Range: -10.7313
Max Act: 10.1688. Min Act: -0.1700
Data Index: 7113123 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19