Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4016 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2245. Min Range: -7.2245
Max Act: 7.2245. Min Act: -0.1700
Data Index: 6255297 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2245. Min Range: -7.2245
Max Act: 7.0995. Min Act: -0.1700
Data Index: 8363367 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2245. Min Range: -7.2245
Max Act: 7.0683. Min Act: -0.1700
Data Index: 6790508 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2245. Min Range: -7.2245
Max Act: 7.0683. Min Act: -0.1700
Data Index: 6574135 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2245. Min Range: -7.2245
Max Act: 7.0058. Min Act: -0.1700
Data Index: 6280026 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2245. Min Range: -7.2245
Max Act: 7.0058. Min Act: -0.1700
Data Index: 2130490 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.9433. Min Act: -0.1700
Data Index: 3357110 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.9745. Min Act: -0.1700
Data Index: 1137079 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.8808. Min Act: -0.1700
Data Index: 7397195 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.8808. Min Act: -0.1700
Data Index: 6734370 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.8808. Min Act: -0.1700
Data Index: 8620848 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.8808. Min Act: -0.1700
Data Index: 1799731 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.8495. Min Act: -0.1700
Data Index: 2004633 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.8495. Min Act: -0.1700
Data Index: 3195875 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.8495. Min Act: -0.1700
Data Index: 7953760 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.8495. Min Act: -0.1700
Data Index: 6360619 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.7870. Min Act: -0.1700
Data Index: 1886712 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.7870. Min Act: -0.1700
Data Index: 5288433 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.7870. Min Act: -0.1700
Data Index: 6280023 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2245. Min Range: -7.2245
Max Act: 6.7870. Min Act: -0.1700
Data Index: 7268491 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19