Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 310 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.3122. Min Act: -0.1700
Data Index: 8427379 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.2808. Min Act: -0.1700
Data Index: 6931278 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.2651. Min Act: -0.1700
Data Index: 699225 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.2337. Min Act: -0.1700
Data Index: 7846213 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.2494. Min Act: -0.1700
Data Index: 4315523 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.2180. Min Act: -0.1700
Data Index: 6666822 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.2022. Min Act: -0.1700
Data Index: 331394 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.2022. Min Act: -0.1700
Data Index: 659555 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.1708. Min Act: -0.1700
Data Index: 3391281 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.1708. Min Act: -0.1700
Data Index: 246219 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.1708. Min Act: -0.1700
Data Index: 6760518 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.1550. Min Act: -0.1700
Data Index: 7217917 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.1708. Min Act: -0.1700
Data Index: 108077 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.1550. Min Act: -0.1700
Data Index: 6054479 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.1393. Min Act: -0.1700
Data Index: 2756777 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.1235. Min Act: -0.1700
Data Index: 4865871 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.0920. Min Act: -0.1700
Data Index: 1862461 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.1078. Min Act: -0.1700
Data Index: 1546483 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.1078. Min Act: -0.1700
Data Index: 4692989 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3122. Min Range: -3.3122
Max Act: 3.0920. Min Act: -0.1700
Data Index: 5562881 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19