Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2858 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1457. Min Range: -5.1457
Max Act: 5.1457. Min Act: -0.1700
Data Index: 2091642 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1457. Min Range: -5.1457
Max Act: 5.0207. Min Act: -0.1700
Data Index: 6340296 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.9270. Min Act: -0.1700
Data Index: 7316807 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.9270. Min Act: -0.1700
Data Index: 7555476 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.9582. Min Act: -0.1700
Data Index: 5219709 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.9270. Min Act: -0.1700
Data Index: 6069241 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.9582. Min Act: -0.1700
Data Index: 416853 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.8957. Min Act: -0.1700
Data Index: 562670 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.9270. Min Act: -0.1700
Data Index: 6309106 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.9270. Min Act: -0.1700
Data Index: 4556780 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.8645. Min Act: -0.1700
Data Index: 8797619 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.8645. Min Act: -0.1700
Data Index: 2789954 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.8957. Min Act: -0.1700
Data Index: 162226 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.8332. Min Act: -0.1700
Data Index: 4811308 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.8020. Min Act: -0.1700
Data Index: 1854271 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.8020. Min Act: -0.1700
Data Index: 301657 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.8020. Min Act: -0.1700
Data Index: 8741270 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.7707. Min Act: -0.1700
Data Index: 5365231 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.7395. Min Act: -0.1700
Data Index: 2119903 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1457. Min Range: -5.1457
Max Act: 4.7082. Min Act: -0.1700
Data Index: 6335355 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19