Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 483 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.6035. Min Act: -0.1700
Data Index: 3660444 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.4785. Min Act: -0.1700
Data Index: 6389144 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.2910. Min Act: -0.1700
Data Index: 3962566 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.2910. Min Act: -0.1700
Data Index: 2934112 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.2598. Min Act: -0.1700
Data Index: 6389143 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.2598. Min Act: -0.1700
Data Index: 7189319 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.1973. Min Act: -0.1700
Data Index: 7330065 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.1660. Min Act: -0.1700
Data Index: 6356196 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.1660. Min Act: -0.1700
Data Index: 104473 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.1348. Min Act: -0.1700
Data Index: 5780253 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.0723. Min Act: -0.1700
Data Index: 6670345 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.0410. Min Act: -0.1700
Data Index: 6484921 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.0098. Min Act: -0.1700
Data Index: 8046403 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6035. Min Range: -7.6035
Max Act: 6.9785. Min Act: -0.1700
Data Index: 4277844 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6035. Min Range: -7.6035
Max Act: 6.9785. Min Act: -0.1700
Data Index: 4079729 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6035. Min Range: -7.6035
Max Act: 7.0098. Min Act: -0.1700
Data Index: 8021690 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6035. Min Range: -7.6035
Max Act: 6.9473. Min Act: -0.1700
Data Index: 8408070 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6035. Min Range: -7.6035
Max Act: 6.9473. Min Act: -0.1700
Data Index: 2358886 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6035. Min Range: -7.6035
Max Act: 6.8535. Min Act: -0.1700
Data Index: 7608773 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6035. Min Range: -7.6035
Max Act: 6.8223. Min Act: -0.1700
Data Index: 2369939 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19