Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.8223. Min Act: -0.1700
Data Index: 704403 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.5723. Min Act: -0.1700
Data Index: 3177426 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.6035. Min Act: -0.1700
Data Index: 5723050 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.5410. Min Act: -0.1700
Data Index: 7969230 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.5410. Min Act: -0.1700
Data Index: 1337098 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.5098. Min Act: -0.1700
Data Index: 390955 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.5098. Min Act: -0.1700
Data Index: 1001636 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.3848. Min Act: -0.1700
Data Index: 5062690 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.3223. Min Act: -0.1700
Data Index: 7895885 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.2910. Min Act: -0.1700
Data Index: 3485976 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.2598. Min Act: -0.1700
Data Index: 5423527 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.2598. Min Act: -0.1700
Data Index: 4921317 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.1973. Min Act: -0.1700
Data Index: 8105473 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.2285. Min Act: -0.1700
Data Index: 7624742 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.1348. Min Act: -0.1700
Data Index: 3515092 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.1660. Min Act: -0.1700
Data Index: 5535008 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.1973. Min Act: -0.1700
Data Index: 4215995 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.1348. Min Act: -0.1700
Data Index: 1157906 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.1348. Min Act: -0.1700
Data Index: 2395002 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8223. Min Range: -5.8223
Max Act: 5.1348. Min Act: -0.1700
Data Index: 8097898 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19