Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.5192. Min Act: -0.1700
Data Index: 6396653 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.5192. Min Act: -0.1700
Data Index: 5263260 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.3942. Min Act: -0.1700
Data Index: 4288093 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.3317. Min Act: -0.1700
Data Index: 1466999 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.2692. Min Act: -0.1700
Data Index: 5143125 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.2379. Min Act: -0.1700
Data Index: 7854724 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.1754. Min Act: -0.1700
Data Index: 849905 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.1442. Min Act: -0.1700
Data Index: 8063778 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.1442. Min Act: -0.1700
Data Index: 93532 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.1442. Min Act: -0.1700
Data Index: 155335 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.1129. Min Act: -0.1700
Data Index: 6489887 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.1129. Min Act: -0.1700
Data Index: 6030449 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.1129. Min Act: -0.1700
Data Index: 1731993 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.1129. Min Act: -0.1700
Data Index: 127372 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.1129. Min Act: -0.1700
Data Index: 7053685 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.0817. Min Act: -0.1700
Data Index: 5656724 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.1129. Min Act: -0.1700
Data Index: 2963730 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.0504. Min Act: -0.1700
Data Index: 6103121 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.0504. Min Act: -0.1700
Data Index: 6821496 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5192. Min Range: -5.5192
Max Act: 5.0504. Min Act: -0.1700
Data Index: 2738008 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19