Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0315. Min Range: -7.0315
Max Act: 7.0315. Min Act: -0.1700
Data Index: 7710206 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.8440. Min Act: -0.1700
Data Index: 2383541 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.7815. Min Act: -0.1700
Data Index: 6059877 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.7503. Min Act: -0.1700
Data Index: 2683515 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.7503. Min Act: -0.1700
Data Index: 399789 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.6878. Min Act: -0.1700
Data Index: 3580592 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.6878. Min Act: -0.1700
Data Index: 5712031 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.6565. Min Act: -0.1700
Data Index: 4329879 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.6253. Min Act: -0.1700
Data Index: 3389086 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.6253. Min Act: -0.1700
Data Index: 6885742 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.6253. Min Act: -0.1700
Data Index: 3499830 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.5940. Min Act: -0.1700
Data Index: 3392866 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.5628. Min Act: -0.1700
Data Index: 6556096 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.5315. Min Act: -0.1700
Data Index: 7917616 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.5315. Min Act: -0.1700
Data Index: 5349739 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.5003. Min Act: -0.1700
Data Index: 7350880 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.4690. Min Act: -0.1700
Data Index: 6769524 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.4378. Min Act: -0.1700
Data Index: 2949027 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.5003. Min Act: -0.1700
Data Index: 1480282 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0315. Min Range: -7.0315
Max Act: 6.4690. Min Act: -0.1700
Data Index: 5748807 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19