Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3402 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.6085. Min Act: -0.1700
Data Index: 6935751 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4835. Min Act: -0.1700
Data Index: 3355467 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.3585. Min Act: -0.1700
Data Index: 1003593 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2960. Min Act: -0.1700
Data Index: 5706919 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2960. Min Act: -0.1700
Data Index: 4394072 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2960. Min Act: -0.1700
Data Index: 7358757 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2335. Min Act: -0.1700
Data Index: 7973158 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2335. Min Act: -0.1700
Data Index: 1003590 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2335. Min Act: -0.1700
Data Index: 7358755 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2335. Min Act: -0.1700
Data Index: 1809989 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.1710. Min Act: -0.1700
Data Index: 7568162 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2335. Min Act: -0.1700
Data Index: 2473838 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.1710. Min Act: -0.1700
Data Index: 4280309 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.1710. Min Act: -0.1700
Data Index: 2779573 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.1085. Min Act: -0.1700
Data Index: 8001425 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.1085. Min Act: -0.1700
Data Index: 196003 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.1085. Min Act: -0.1700
Data Index: 7947988 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.1085. Min Act: -0.1700
Data Index: 6149539 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.0460. Min Act: -0.1700
Data Index: 1761251 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.0460. Min Act: -0.1700
Data Index: 2800706 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19