Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1043 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5397. Min Range: -6.5397
Max Act: 6.5397. Min Act: -0.1700
Data Index: 4429812 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5397. Min Range: -6.5397
Max Act: 6.2584. Min Act: -0.1700
Data Index: 2981642 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5397. Min Range: -6.5397
Max Act: 6.1959. Min Act: -0.1700
Data Index: 1905297 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5397. Min Range: -6.5397
Max Act: 6.1959. Min Act: -0.1700
Data Index: 5917419 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5397. Min Range: -6.5397
Max Act: 6.0397. Min Act: -0.1700
Data Index: 7429562 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.9772. Min Act: -0.1700
Data Index: 4463646 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.9147. Min Act: -0.1700
Data Index: 5909683 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.9147. Min Act: -0.1700
Data Index: 1536664 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.9459. Min Act: -0.1700
Data Index: 1479366 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.9147. Min Act: -0.1700
Data Index: 7054137 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.8834. Min Act: -0.1700
Data Index: 5056609 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.8834. Min Act: -0.1700
Data Index: 7674051 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.8522. Min Act: -0.1700
Data Index: 1114507 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.8209. Min Act: -0.1700
Data Index: 8516416 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.8209. Min Act: -0.1700
Data Index: 2947555 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.8522. Min Act: -0.1700
Data Index: 394470 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.8209. Min Act: -0.1700
Data Index: 4461416 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.7897. Min Act: -0.1700
Data Index: 7033787 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.8522. Min Act: -0.1700
Data Index: 5195282 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5397. Min Range: -6.5397
Max Act: 5.8209. Min Act: -0.1700
Data Index: 1571090 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19