Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3577 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.9809. Min Act: -0.1700
Data Index: 7657661 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.5121. Min Act: -0.1700
Data Index: 3312916 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4809. Min Act: -0.1700
Data Index: 5289908 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4496. Min Act: -0.1700
Data Index: 3955376 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4809. Min Act: -0.1700
Data Index: 6591411 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4809. Min Act: -0.1700
Data Index: 8821536 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4809. Min Act: -0.1700
Data Index: 5555348 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4809. Min Act: -0.1700
Data Index: 7021890 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4809. Min Act: -0.1700
Data Index: 5289907 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4184. Min Act: -0.1700
Data Index: 3139814 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4496. Min Act: -0.1700
Data Index: 7455707 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4496. Min Act: -0.1700
Data Index: 5201074 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.4496. Min Act: -0.1700
Data Index: 924940 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.3871. Min Act: -0.1700
Data Index: 4613493 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.3559. Min Act: -0.1700
Data Index: 7277785 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.3559. Min Act: -0.1700
Data Index: 4117973 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.3559. Min Act: -0.1700
Data Index: 3006234 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.3246. Min Act: -0.1700
Data Index: 7819142 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.3246. Min Act: -0.1700
Data Index: 8781088 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9809. Min Range: -7.9809
Max Act: 7.2934. Min Act: -0.1700
Data Index: 4999709 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19