Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 396 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.5856. Min Act: -0.1700
Data Index: 5657476 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.6013. Min Act: -0.1700
Data Index: 1117728 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.5543. Min Act: -0.1700
Data Index: 3750265 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.4760. Min Act: -0.1700
Data Index: 5393492 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.4603. Min Act: -0.1700
Data Index: 4139362 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.4447. Min Act: -0.1700
Data Index: 2304097 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.4447. Min Act: -0.1700
Data Index: 1446939 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.4603. Min Act: -0.1700
Data Index: 534579 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.4290. Min Act: -0.1700
Data Index: 5340223 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.4133. Min Act: -0.1700
Data Index: 4566780 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.4133. Min Act: -0.1700
Data Index: 8613155 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.3977. Min Act: -0.1700
Data Index: 8798129 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.3977. Min Act: -0.1700
Data Index: 5765200 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.3820. Min Act: -0.1700
Data Index: 3534340 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.3977. Min Act: -0.1700
Data Index: 8166344 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.3820. Min Act: -0.1700
Data Index: 4999728 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.3663. Min Act: -0.1700
Data Index: 5926838 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.3663. Min Act: -0.1700
Data Index: 2709991 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.3820. Min Act: -0.1700
Data Index: 6360814 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6013. Min Range: -3.6013
Max Act: 3.3663. Min Act: -0.1700
Data Index: 5968305 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19