Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 598 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.6346. Min Act: -0.1700
Data Index: 4164352 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.4784. Min Act: -0.1700
Data Index: 4164351 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.4471. Min Act: -0.1700
Data Index: 655390 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.3846. Min Act: -0.1700
Data Index: 1718572 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.3221. Min Act: -0.1700
Data Index: 6984924 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.1346. Min Act: -0.1700
Data Index: 153445 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.1034. Min Act: -0.1700
Data Index: 2840017 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.1034. Min Act: -0.1700
Data Index: 5095992 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.1346. Min Act: -0.1700
Data Index: 5351800 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.0721. Min Act: -0.1700
Data Index: 1004008 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.0409. Min Act: -0.1700
Data Index: 6791126 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.0096. Min Act: -0.1700
Data Index: 7485185 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.0409. Min Act: -0.1700
Data Index: 3389951 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.0096. Min Act: -0.1700
Data Index: 2124144 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6346. Min Range: -5.6346
Max Act: 5.0409. Min Act: -0.1700
Data Index: 6810648 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6346. Min Range: -5.6346
Max Act: 4.9784. Min Act: -0.1700
Data Index: 5281036 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6346. Min Range: -5.6346
Max Act: 4.9784. Min Act: -0.1700
Data Index: 1694644 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6346. Min Range: -5.6346
Max Act: 4.9784. Min Act: -0.1700
Data Index: 4910140 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6346. Min Range: -5.6346
Max Act: 4.9471. Min Act: -0.1700
Data Index: 3613987 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6346. Min Range: -5.6346
Max Act: 4.9784. Min Act: -0.1700
Data Index: 2023210 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19