Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.8974. Min Act: -0.1700
Data Index: 6099168 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.8349. Min Act: -0.1700
Data Index: 8443053 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.7724. Min Act: -0.1700
Data Index: 2459554 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.7724. Min Act: -0.1700
Data Index: 1101558 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.7724. Min Act: -0.1700
Data Index: 4815012 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.7411. Min Act: -0.1700
Data Index: 1288195 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.7099. Min Act: -0.1700
Data Index: 3836800 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.7099. Min Act: -0.1700
Data Index: 720272 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.7099. Min Act: -0.1700
Data Index: 205426 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.7099. Min Act: -0.1700
Data Index: 4376703 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.6786. Min Act: -0.1700
Data Index: 6140621 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.6161. Min Act: -0.1700
Data Index: 139608 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.6161. Min Act: -0.1700
Data Index: 1555304 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.6161. Min Act: -0.1700
Data Index: 7946768 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.5849. Min Act: -0.1700
Data Index: 4396776 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.6161. Min Act: -0.1700
Data Index: 898237 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.5536. Min Act: -0.1700
Data Index: 2949081 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.5849. Min Act: -0.1700
Data Index: 4498874 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.5536. Min Act: -0.1700
Data Index: 8370066 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8974. Min Range: -6.8974
Max Act: 6.5536. Min Act: -0.1700
Data Index: 6960807 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19