Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5095 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1709. Min Range: -12.1709
Max Act: 12.1709. Min Act: -0.1700
Data Index: 3609003 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1709. Min Range: -12.1709
Max Act: 12.0459. Min Act: -0.1700
Data Index: 1255412 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.7959. Min Act: -0.1700
Data Index: 1199506 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.6709. Min Act: -0.1700
Data Index: 6918364 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.6084. Min Act: -0.1700
Data Index: 789414 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.6084. Min Act: -0.1700
Data Index: 5099202 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.6084. Min Act: -0.1700
Data Index: 3391576 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.4834. Min Act: -0.1700
Data Index: 6412694 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.4834. Min Act: -0.1700
Data Index: 8355989 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.3584. Min Act: -0.1699
Data Index: 6273576 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.3584. Min Act: -0.1699
Data Index: 4015991 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.2959. Min Act: -0.1700
Data Index: 5106913 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.2334. Min Act: -0.1700
Data Index: 7206687 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.2334. Min Act: -0.1700
Data Index: 2167668 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.2334. Min Act: -0.1700
Data Index: 4611307 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.2334. Min Act: -0.1699
Data Index: 1873698 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.2334. Min Act: -0.1700
Data Index: 4103033 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.1709. Min Act: -0.1700
Data Index: 7108886 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.1709. Min Act: -0.1700
Data Index: 6936414 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1709. Min Range: -12.1709
Max Act: 11.1709. Min Act: -0.1700
Data Index: 1540608 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19