Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3243 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.8637. Min Act: -0.1700
Data Index: 4383394 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.6137. Min Act: -0.1700
Data Index: 7373515 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.4262. Min Act: -0.1700
Data Index: 1010111 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.3324. Min Act: -0.1700
Data Index: 6750842 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.3324. Min Act: -0.1700
Data Index: 1080358 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.2699. Min Act: -0.1700
Data Index: 8039328 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.2387. Min Act: -0.1700
Data Index: 5048596 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.2387. Min Act: -0.1700
Data Index: 1177729 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.2074. Min Act: -0.1700
Data Index: 706985 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.1762. Min Act: -0.1700
Data Index: 8355432 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.1762. Min Act: -0.1700
Data Index: 3428508 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.1449. Min Act: -0.1700
Data Index: 2260872 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.1449. Min Act: -0.1700
Data Index: 3690744 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.0512. Min Act: -0.1700
Data Index: 678557 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.0199. Min Act: -0.1700
Data Index: 4920367 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.0199. Min Act: -0.1700
Data Index: 1871207 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.0199. Min Act: -0.1700
Data Index: 7932290 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.0199. Min Act: -0.1700
Data Index: 5906812 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8637. Min Range: -6.8637
Max Act: 6.0199. Min Act: -0.1700
Data Index: 8049575 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8637. Min Range: -6.8637
Max Act: 5.9887. Min Act: -0.1700
Data Index: 7299721 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19