Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4285 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0439. Min Range: -5.0439
Max Act: 5.0439. Min Act: -0.1700
Data Index: 1037526 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.9189. Min Act: -0.1700
Data Index: 1308509 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.8564. Min Act: -0.1700
Data Index: 5454785 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7939. Min Act: -0.1700
Data Index: 5788899 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.8252. Min Act: -0.1700
Data Index: 4048250 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7939. Min Act: -0.1700
Data Index: 2130041 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7939. Min Act: -0.1700
Data Index: 6864297 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7939. Min Act: -0.1700
Data Index: 6769594 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7627. Min Act: -0.1700
Data Index: 3256264 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7627. Min Act: -0.1700
Data Index: 2809641 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7627. Min Act: -0.1700
Data Index: 2887399 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7627. Min Act: -0.1700
Data Index: 537326 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7627. Min Act: -0.1700
Data Index: 5376404 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7939. Min Act: -0.1700
Data Index: 5471237 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7627. Min Act: -0.1700
Data Index: 5560857 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7627. Min Act: -0.1700
Data Index: 3224972 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7314. Min Act: -0.1700
Data Index: 39816 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7314. Min Act: -0.1700
Data Index: 8214854 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7314. Min Act: -0.1700
Data Index: 1266038 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0439. Min Range: -5.0439
Max Act: 4.7002. Min Act: -0.1700
Data Index: 1558888 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19