Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6365 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4743. Min Range: -8.4743
Max Act: 8.4743. Min Act: -0.1700
Data Index: 7694735 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4743. Min Range: -8.4743
Max Act: 8.0368. Min Act: -0.1700
Data Index: 2620966 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.8493. Min Act: -0.1700
Data Index: 5358730 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.8180. Min Act: -0.1700
Data Index: 436222 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.8180. Min Act: -0.1700
Data Index: 6629323 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.8180. Min Act: -0.1700
Data Index: 1441124 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.7555. Min Act: -0.1700
Data Index: 6747339 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.6930. Min Act: -0.1700
Data Index: 2472255 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.6930. Min Act: -0.1700
Data Index: 6084314 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.6305. Min Act: -0.1700
Data Index: 5543341 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.6618. Min Act: -0.1700
Data Index: 1068226 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.5993. Min Act: -0.1700
Data Index: 7579492 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.5680. Min Act: -0.1700
Data Index: 8625089 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.5993. Min Act: -0.1700
Data Index: 2045007 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.5993. Min Act: -0.1700
Data Index: 7697994 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.5055. Min Act: -0.1700
Data Index: 7652808 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.5368. Min Act: -0.1700
Data Index: 8655119 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.5055. Min Act: -0.1700
Data Index: 568152 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.5055. Min Act: -0.1700
Data Index: 5747015 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4743. Min Range: -8.4743
Max Act: 7.4743. Min Act: -0.1700
Data Index: 1766738 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19