Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.9238. Min Act: -0.1700
Data Index: 8757587 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.9238. Min Act: -0.1700
Data Index: 1778146 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.8926. Min Act: -0.1700
Data Index: 692410 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.8613. Min Act: -0.1700
Data Index: 4371812 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.8301. Min Act: -0.1700
Data Index: 2170454 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.8301. Min Act: -0.1700
Data Index: 4213696 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.8301. Min Act: -0.1700
Data Index: 3852161 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.8301. Min Act: -0.1700
Data Index: 944173 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7988. Min Act: -0.1700
Data Index: 1954700 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7988. Min Act: -0.1700
Data Index: 781898 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7988. Min Act: -0.1700
Data Index: 4501390 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7988. Min Act: -0.1700
Data Index: 2365853 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7988. Min Act: -0.1700
Data Index: 7699124 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7676. Min Act: -0.1700
Data Index: 4792346 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7676. Min Act: -0.1700
Data Index: 1909196 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7676. Min Act: -0.1700
Data Index: 2201761 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7676. Min Act: -0.1700
Data Index: 4191551 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7676. Min Act: -0.1700
Data Index: 4155534 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7676. Min Act: -0.1700
Data Index: 3578823 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9238. Min Range: -4.9238
Max Act: 4.7676. Min Act: -0.1700
Data Index: 1106023 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19