Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5184 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.8555. Min Act: -0.1700
Data Index: 4552633 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.5743. Min Act: -0.1700
Data Index: 3753076 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.4493. Min Act: -0.1700
Data Index: 5130169 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.4180. Min Act: -0.1700
Data Index: 6658841 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.2618. Min Act: -0.1700
Data Index: 8375278 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.2305. Min Act: -0.1700
Data Index: 2175110 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.2618. Min Act: -0.1700
Data Index: 3503960 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1993. Min Act: -0.1700
Data Index: 6772549 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1993. Min Act: -0.1700
Data Index: 4683503 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1993. Min Act: -0.1700
Data Index: 8305492 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1993. Min Act: -0.1700
Data Index: 8144335 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1993. Min Act: -0.1700
Data Index: 2879910 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1680. Min Act: -0.1700
Data Index: 7883748 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1680. Min Act: -0.1700
Data Index: 990440 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1368. Min Act: -0.1700
Data Index: 5036068 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1368. Min Act: -0.1700
Data Index: 5063484 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1055. Min Act: -0.1700
Data Index: 2749133 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1055. Min Act: -0.1700
Data Index: 2324597 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1055. Min Act: -0.1700
Data Index: 5346093 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8555. Min Range: -6.8555
Max Act: 6.1368. Min Act: -0.1700
Data Index: 345660 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19