Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1146 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.9383. Min Act: -0.1700
Data Index: 8002126 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.9383. Min Act: -0.1700
Data Index: 5223947 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.8758. Min Act: -0.1700
Data Index: 1084282 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.9070. Min Act: -0.1700
Data Index: 3089492 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.8445. Min Act: -0.1700
Data Index: 8423719 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.8445. Min Act: -0.1700
Data Index: 2097018 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.8445. Min Act: -0.1700
Data Index: 624434 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.7508. Min Act: -0.1700
Data Index: 7244233 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.8133. Min Act: -0.1700
Data Index: 3235664 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.8133. Min Act: -0.1700
Data Index: 627784 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.8133. Min Act: -0.1700
Data Index: 817500 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.7820. Min Act: -0.1700
Data Index: 6798330 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.8133. Min Act: -0.1700
Data Index: 1971119 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.7820. Min Act: -0.1700
Data Index: 6169876 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.7820. Min Act: -0.1700
Data Index: 3184210 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.7820. Min Act: -0.1700
Data Index: 707594 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.7820. Min Act: -0.1700
Data Index: 7598186 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.7195. Min Act: -0.1700
Data Index: 6505870 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.7508. Min Act: -0.1700
Data Index: 2672938 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9383. Min Range: -4.9383
Max Act: 4.7508. Min Act: -0.1700
Data Index: 4319372 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19