Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 873 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.9331. Min Act: -0.1687
Data Index: 2001131 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.8220. Min Act: -0.1699
Data Index: 32249 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.8134. Min Act: -0.1700
Data Index: 4004542 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.8048. Min Act: -0.1700
Data Index: 5412179 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7876. Min Act: -0.1700
Data Index: 3930149 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7790. Min Act: -0.1700
Data Index: 1349847 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7704. Min Act: -0.1699
Data Index: 4406211 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7704. Min Act: -0.1700
Data Index: 3896183 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7531. Min Act: -0.1700
Data Index: 1748991 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7618. Min Act: -0.1700
Data Index: 6132880 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7531. Min Act: -0.1700
Data Index: 3520099 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7618. Min Act: -0.1700
Data Index: 2406344 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7358. Min Act: -0.1700
Data Index: 8190376 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7358. Min Act: -0.1700
Data Index: 1804936 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7272. Min Act: -0.1700
Data Index: 4750134 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7358. Min Act: -0.1700
Data Index: 3191837 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7185. Min Act: -0.1700
Data Index: 572585 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7099. Min Act: -0.1700
Data Index: 3902021 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7012. Min Act: -0.1700
Data Index: 3301437 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9331. Min Range: -1.9331
Max Act: 1.7012. Min Act: -0.1700
Data Index: 1640683 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19