Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6356 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.5352. Min Act: -0.1700
Data Index: 8059901 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.5039. Min Act: -0.1700
Data Index: 5559741 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.5039. Min Act: -0.1700
Data Index: 1265530 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.4727. Min Act: -0.1700
Data Index: 1190354 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.4414. Min Act: -0.1700
Data Index: 7152184 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.4102. Min Act: -0.1700
Data Index: 3706865 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.4102. Min Act: -0.1700
Data Index: 867782 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.4102. Min Act: -0.1700
Data Index: 5372881 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.4102. Min Act: -0.1700
Data Index: 2047527 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.4414. Min Act: -0.1700
Data Index: 8507038 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3789. Min Act: -0.1700
Data Index: 5899951 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3477. Min Act: -0.1700
Data Index: 4416193 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3477. Min Act: -0.1700
Data Index: 4548381 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3477. Min Act: -0.1700
Data Index: 7160964 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3477. Min Act: -0.1700
Data Index: 6338658 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3477. Min Act: -0.1700
Data Index: 4246431 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3477. Min Act: -0.1700
Data Index: 1723456 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3477. Min Act: -0.1700
Data Index: 5987516 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3477. Min Act: -0.1700
Data Index: 1096346 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3164. Min Act: -0.1700
Data Index: 4045794 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19