Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0129. Min Range: -2.0129
Max Act: 2.0129. Min Act: -0.1700
Data Index: 6901188 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9791. Min Act: -0.1700
Data Index: 1339265 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9622. Min Act: -0.1700
Data Index: 8099403 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9452. Min Act: -0.1700
Data Index: 6481635 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9282. Min Act: -0.1700
Data Index: 8704675 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9282. Min Act: -0.1700
Data Index: 382395 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9452. Min Act: -0.1700
Data Index: 3611865 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9112. Min Act: -0.1700
Data Index: 3848374 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9112. Min Act: -0.1700
Data Index: 6056520 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9112. Min Act: -0.1700
Data Index: 1779445 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.8941. Min Act: -0.1700
Data Index: 4759838 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.8941. Min Act: -0.1700
Data Index: 7015096 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.8770. Min Act: -0.1700
Data Index: 1905880 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.8941. Min Act: -0.1700
Data Index: 8421054 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.8941. Min Act: -0.1700
Data Index: 1024942 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9112. Min Act: -0.1700
Data Index: 8120548 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.9112. Min Act: -0.1700
Data Index: 5059269 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.8770. Min Act: -0.1700
Data Index: 2570352 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.8770. Min Act: -0.1700
Data Index: 2703291 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0129. Min Range: -2.0129
Max Act: 1.8770. Min Act: -0.1700
Data Index: 497302 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19