Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1578 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1205. Min Range: -3.1205
Max Act: 3.1205. Min Act: -0.1700
Data Index: 2583541 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.9310. Min Act: -0.1700
Data Index: 5705111 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.9152. Min Act: -0.1700
Data Index: 7445002 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.8835. Min Act: -0.1700
Data Index: 5901292 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.8517. Min Act: -0.1700
Data Index: 3940875 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.8199. Min Act: -0.1700
Data Index: 1366173 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.8040. Min Act: -0.1700
Data Index: 8299624 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.8199. Min Act: -0.1700
Data Index: 1931722 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.8199. Min Act: -0.1700
Data Index: 6874603 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7881. Min Act: -0.1700
Data Index: 5012407 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7881. Min Act: -0.1700
Data Index: 3785967 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7881. Min Act: -0.1700
Data Index: 6474108 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7562. Min Act: -0.1700
Data Index: 5049797 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7562. Min Act: -0.1700
Data Index: 4760475 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7721. Min Act: -0.1700
Data Index: 8668862 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7402. Min Act: -0.1700
Data Index: 8277853 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7402. Min Act: -0.1700
Data Index: 5584941 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7242. Min Act: -0.1700
Data Index: 5559663 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7402. Min Act: -0.1700
Data Index: 8091012 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1205. Min Range: -3.1205
Max Act: 2.7562. Min Act: -0.1700
Data Index: 2080528 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19