Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.8117. Min Act: -0.1700
Data Index: 2030584 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5927. Min Act: -0.1700
Data Index: 4004919 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5771. Min Act: -0.1700
Data Index: 5499493 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5458. Min Act: -0.1700
Data Index: 3432104 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5301. Min Act: -0.1700
Data Index: 5097257 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4988. Min Act: -0.1700
Data Index: 6331668 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.5144. Min Act: -0.1700
Data Index: 1798486 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4831. Min Act: -0.1700
Data Index: 7389288 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4674. Min Act: -0.1700
Data Index: 806635 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4518. Min Act: -0.1700
Data Index: 6021701 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4518. Min Act: -0.1700
Data Index: 4269563 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4518. Min Act: -0.1700
Data Index: 2094581 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4518. Min Act: -0.1700
Data Index: 7927161 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4361. Min Act: -0.1700
Data Index: 5897714 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4204. Min Act: -0.1700
Data Index: 5201278 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4204. Min Act: -0.1700
Data Index: 3418638 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.4048. Min Act: -0.1700
Data Index: 8752939 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.3891. Min Act: -0.1700
Data Index: 7239173 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.3891. Min Act: -0.1700
Data Index: 1152809 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8117. Min Range: -3.8117
Max Act: 3.3891. Min Act: -0.1700
Data Index: 6967515 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19