Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5754 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9187. Min Range: -7.9187
Max Act: 7.9187. Min Act: -0.1700
Data Index: 6862034 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.9812. Min Act: -0.1700
Data Index: 4752243 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.8874. Min Act: -0.1700
Data Index: 6659564 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.7937. Min Act: -0.1700
Data Index: 2089971 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.8249. Min Act: -0.1700
Data Index: 980204 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.7312. Min Act: -0.1700
Data Index: 4126790 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.6687. Min Act: -0.1700
Data Index: 4917744 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.6062. Min Act: -0.1700
Data Index: 5207510 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.5437. Min Act: -0.1700
Data Index: 5756793 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.5124. Min Act: -0.1700
Data Index: 3873708 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.5124. Min Act: -0.1700
Data Index: 2820571 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.4812. Min Act: -0.1700
Data Index: 6314360 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.4812. Min Act: -0.1700
Data Index: 3125226 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.4812. Min Act: -0.1700
Data Index: 1328504 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.4812. Min Act: -0.1700
Data Index: 6644112 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.4499. Min Act: -0.1700
Data Index: 6432363 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.4499. Min Act: -0.1700
Data Index: 5607853 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.4187. Min Act: -0.1700
Data Index: 7217748 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.3874. Min Act: -0.1700
Data Index: 7154533 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9187. Min Range: -7.9187
Max Act: 6.3874. Min Act: -0.1700
Data Index: 7976994 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19