Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1205. Min Range: -5.1205
Max Act: 5.1205. Min Act: -0.1700
Data Index: 5917982 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1205. Min Range: -5.1205
Max Act: 5.0580. Min Act: -0.1700
Data Index: 1987775 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1205. Min Range: -5.1205
Max Act: 5.0580. Min Act: -0.1700
Data Index: 3506059 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.9642. Min Act: -0.1700
Data Index: 8239903 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.9330. Min Act: -0.1700
Data Index: 6642625 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.9330. Min Act: -0.1700
Data Index: 5156026 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.9642. Min Act: -0.1700
Data Index: 7142602 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.9330. Min Act: -0.1700
Data Index: 8791848 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.9017. Min Act: -0.1700
Data Index: 8287290 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.9017. Min Act: -0.1700
Data Index: 2529945 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.9017. Min Act: -0.1700
Data Index: 457233 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.8392. Min Act: -0.1700
Data Index: 2873229 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.8705. Min Act: -0.1700
Data Index: 7401122 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.9017. Min Act: -0.1700
Data Index: 7219834 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.9017. Min Act: -0.1700
Data Index: 3254489 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.8705. Min Act: -0.1700
Data Index: 6958688 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.8392. Min Act: -0.1700
Data Index: 4947120 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.8392. Min Act: -0.1700
Data Index: 5182408 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.8392. Min Act: -0.1700
Data Index: 1309244 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1205. Min Range: -5.1205
Max Act: 4.8705. Min Act: -0.1700
Data Index: 7402830 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19