Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.7386. Min Act: -0.1700
Data Index: 2892594 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.5823. Min Act: -0.1700
Data Index: 5946402 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.4886. Min Act: -0.1700
Data Index: 4738386 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.4886. Min Act: -0.1700
Data Index: 522969 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.4573. Min Act: -0.1700
Data Index: 7400300 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.4261. Min Act: -0.1700
Data Index: 7627092 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.3948. Min Act: -0.1700
Data Index: 2001462 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.3323. Min Act: -0.1700
Data Index: 6252837 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.3323. Min Act: -0.1700
Data Index: 4198748 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.2386. Min Act: -0.1700
Data Index: 6529614 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.2698. Min Act: -0.1700
Data Index: 4173345 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.2698. Min Act: -0.1700
Data Index: 7113729 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.2386. Min Act: -0.1700
Data Index: 8692863 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.2386. Min Act: -0.1700
Data Index: 3826320 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.2386. Min Act: -0.1700
Data Index: 359553 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.2073. Min Act: -0.1700
Data Index: 797801 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.2073. Min Act: -0.1700
Data Index: 5365013 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 7184622 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.1448. Min Act: -0.1700
Data Index: 4382406 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7386. Min Range: -5.7386
Max Act: 5.1448. Min Act: -0.1700
Data Index: 2616483 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19