Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1531 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.9137. Min Act: -0.1696
Data Index: 4364144 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8625. Min Act: -0.1700
Data Index: 8781319 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8625. Min Act: -0.1700
Data Index: 6692261 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8539. Min Act: -0.1700
Data Index: 5082286 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8539. Min Act: -0.1696
Data Index: 3529225 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8368. Min Act: -0.1700
Data Index: 2411707 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8368. Min Act: -0.1700
Data Index: 1384022 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8282. Min Act: -0.1700
Data Index: 3564869 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8368. Min Act: -0.1700
Data Index: 3305584 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8196. Min Act: -0.1700
Data Index: 2596680 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8110. Min Act: -0.1696
Data Index: 6564140 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8196. Min Act: -0.1700
Data Index: 4366339 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7938. Min Act: -0.1700
Data Index: 8508713 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8025. Min Act: -0.1700
Data Index: 2151519 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8025. Min Act: -0.1700
Data Index: 564551 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8025. Min Act: -0.1700
Data Index: 5827200 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.8025. Min Act: -0.1700
Data Index: 442101 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7938. Min Act: -0.1696
Data Index: 1779985 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7852. Min Act: -0.1700
Data Index: 1597186 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7852. Min Act: -0.1700
Data Index: 844097 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19