Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5742 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.9297. Min Act: -0.1700
Data Index: 5124282 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.7733. Min Act: -0.1700
Data Index: 1979021 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.6169. Min Act: -0.1700
Data Index: 5036901 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.5543. Min Act: -0.1700
Data Index: 3951386 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.5543. Min Act: -0.1700
Data Index: 2138319 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.5543. Min Act: -0.1700
Data Index: 5804982 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.5386. Min Act: -0.1700
Data Index: 7325747 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.5386. Min Act: -0.1700
Data Index: 5169506 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.5386. Min Act: -0.1700
Data Index: 6860939 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.5386. Min Act: -0.1700
Data Index: 6288147 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.5230. Min Act: -0.1700
Data Index: 5851437 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.5073. Min Act: -0.1700
Data Index: 3877708 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.4916. Min Act: -0.1700
Data Index: 322676 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.4916. Min Act: -0.1700
Data Index: 4860527 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.4916. Min Act: -0.1700
Data Index: 2087785 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.4760. Min Act: -0.1700
Data Index: 6668679 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.4446. Min Act: -0.1700
Data Index: 4314755 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.4603. Min Act: -0.1700
Data Index: 2260290 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.4446. Min Act: -0.1700
Data Index: 5559774 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9297. Min Range: -3.9297
Max Act: 3.4446. Min Act: -0.1700
Data Index: 2593288 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19