Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0076. Min Range: -9.0076
Max Act: 9.0076. Min Act: -0.1700
Data Index: 8159335 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.8826. Min Act: -0.1700
Data Index: 201420 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.8201. Min Act: -0.1700
Data Index: 3139187 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.8826. Min Act: -0.1700
Data Index: 6473707 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.7576. Min Act: -0.1700
Data Index: 7973131 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.6951. Min Act: -0.1700
Data Index: 8298222 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.6951. Min Act: -0.1700
Data Index: 8602329 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.6951. Min Act: -0.1700
Data Index: 4916881 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.6326. Min Act: -0.1700
Data Index: 6104281 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.6326. Min Act: -0.1700
Data Index: 2781562 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.6326. Min Act: -0.1700
Data Index: 5476379 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.5701. Min Act: -0.1700
Data Index: 5402826 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.5076. Min Act: -0.1700
Data Index: 3237469 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.5076. Min Act: -0.1700
Data Index: 5780252 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.5701. Min Act: -0.1700
Data Index: 7755422 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.4451. Min Act: -0.1700
Data Index: 5484222 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.5076. Min Act: -0.1700
Data Index: 4939879 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.5076. Min Act: -0.1700
Data Index: 5518775 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.5076. Min Act: -0.1700
Data Index: 8579503 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0076. Min Range: -9.0076
Max Act: 8.5076. Min Act: -0.1700
Data Index: 7367574 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19