Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.5387. Min Act: -0.1700
Data Index: 7475071 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.5074. Min Act: -0.1700
Data Index: 6196743 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.4762. Min Act: -0.1700
Data Index: 6416957 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.4449. Min Act: -0.1700
Data Index: 4819228 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.3824. Min Act: -0.1700
Data Index: 6323906 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.3824. Min Act: -0.1700
Data Index: 5490636 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.3824. Min Act: -0.1700
Data Index: 482912 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.3824. Min Act: -0.1700
Data Index: 3972140 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.3824. Min Act: -0.1700
Data Index: 4828859 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.3512. Min Act: -0.1700
Data Index: 2992088 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.3199. Min Act: -0.1700
Data Index: 3965785 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.3512. Min Act: -0.1700
Data Index: 916965 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.3512. Min Act: -0.1700
Data Index: 5163028 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.3512. Min Act: -0.1700
Data Index: 7192973 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.2887. Min Act: -0.1700
Data Index: 4296269 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.2887. Min Act: -0.1700
Data Index: 7634788 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.2887. Min Act: -0.1700
Data Index: 3461266 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.2574. Min Act: -0.1700
Data Index: 6162260 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.2887. Min Act: -0.1700
Data Index: 5432720 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5387. Min Range: -6.5387
Max Act: 6.2887. Min Act: -0.1700
Data Index: 7056548 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19