Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 411 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.6372. Min Act: -0.1699
Data Index: 8377804 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.6213. Min Act: -0.1698
Data Index: 4925311 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.6134. Min Act: -0.1696
Data Index: 4320840 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5976. Min Act: -0.1680
Data Index: 1188955 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5819. Min Act: -0.1700
Data Index: 1831262 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5741. Min Act: -0.1700
Data Index: 1069054 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5741. Min Act: -0.1691
Data Index: 1158219 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5819. Min Act: -0.1694
Data Index: 4351070 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5741. Min Act: -0.1675
Data Index: 8502149 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5741. Min Act: -0.1700
Data Index: 8589567 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5586. Min Act: -0.1700
Data Index: 3498837 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5586. Min Act: -0.1700
Data Index: 5840724 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5586. Min Act: -0.1697
Data Index: 7025310 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5203. Min Act: -0.1697
Data Index: 2506504 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5586. Min Act: -0.1659
Data Index: 7008971 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5356. Min Act: -0.1700
Data Index: 1914045 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5279. Min Act: -0.1700
Data Index: 267597 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5432. Min Act: -0.1629
Data Index: 6422819 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5203. Min Act: -0.1698
Data Index: 2864322 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6372. Min Range: -0.6372
Max Act: 0.5432. Min Act: -0.1700
Data Index: 7402597 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19