Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5951 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.5228. Min Act: -0.1700
Data Index: 748493 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.4603. Min Act: -0.1700
Data Index: 7565796 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.4603. Min Act: -0.1700
Data Index: 3894121 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.3978. Min Act: -0.1700
Data Index: 5515526 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.3353. Min Act: -0.1700
Data Index: 735379 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.3353. Min Act: -0.1700
Data Index: 3129682 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.2728. Min Act: -0.1700
Data Index: 1400284 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.3353. Min Act: -0.1700
Data Index: 3137480 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.2103. Min Act: -0.1700
Data Index: 5626494 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.1478. Min Act: -0.1700
Data Index: 2944565 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.1478. Min Act: -0.1700
Data Index: 2019482 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.1478. Min Act: -0.1700
Data Index: 5728345 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.1478. Min Act: -0.1700
Data Index: 7042092 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.1478. Min Act: -0.1700
Data Index: 4107546 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.1478. Min Act: -0.1700
Data Index: 2638027 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.0853. Min Act: -0.1700
Data Index: 4710132 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.0228. Min Act: -0.1700
Data Index: 233591 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.0853. Min Act: -0.1700
Data Index: 3259079 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.0853. Min Act: -0.1700
Data Index: 368454 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5228. Min Range: -12.5228
Max Act: 12.0853. Min Act: -0.1700
Data Index: 3266796 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19