Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4091 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.7459. Min Act: -0.1700
Data Index: 8677152 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.6834. Min Act: -0.1700
Data Index: 4591208 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.7147. Min Act: -0.1700
Data Index: 743703 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.6209. Min Act: -0.1700
Data Index: 7912333 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.6522. Min Act: -0.1700
Data Index: 1011319 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5897. Min Act: -0.1700
Data Index: 2763564 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5584. Min Act: -0.1700
Data Index: 2316025 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5897. Min Act: -0.1700
Data Index: 4618698 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5584. Min Act: -0.1700
Data Index: 7392991 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5584. Min Act: -0.1700
Data Index: 3963018 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5584. Min Act: -0.1700
Data Index: 1866935 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5584. Min Act: -0.1700
Data Index: 144388 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5272. Min Act: -0.1700
Data Index: 1334205 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5584. Min Act: -0.1700
Data Index: 361762 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5584. Min Act: -0.1700
Data Index: 2776772 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5897. Min Act: -0.1700
Data Index: 8332213 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5584. Min Act: -0.1698
Data Index: 5741097 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.4959. Min Act: -0.1700
Data Index: 6815853 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5272. Min Act: -0.1700
Data Index: 4860918 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7459. Min Range: -4.7459
Max Act: 4.5272. Min Act: -0.1700
Data Index: 6985136 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19