Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.9387. Min Act: -0.1700
Data Index: 2821955 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.9074. Min Act: -0.1700
Data Index: 8629059 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.7824. Min Act: -0.1700
Data Index: 3006854 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.6574. Min Act: -0.1700
Data Index: 3776836 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.6262. Min Act: -0.1700
Data Index: 3451578 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.5324. Min Act: -0.1700
Data Index: 219395 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.5324. Min Act: -0.1700
Data Index: 5898751 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.4699. Min Act: -0.1700
Data Index: 5152831 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.4699. Min Act: -0.1700
Data Index: 1759257 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.4699. Min Act: -0.1700
Data Index: 2232898 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.4699. Min Act: -0.1700
Data Index: 3586727 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.4699. Min Act: -0.1700
Data Index: 1211925 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.4699. Min Act: -0.1700
Data Index: 1075776 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.4074. Min Act: -0.1700
Data Index: 1920389 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.4074. Min Act: -0.1700
Data Index: 3233348 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.3762. Min Act: -0.1700
Data Index: 1223791 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.4074. Min Act: -0.1700
Data Index: 731328 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.3762. Min Act: -0.1700
Data Index: 1054647 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.3449. Min Act: -0.1700
Data Index: 1233382 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9387. Min Range: -5.9387
Max Act: 5.2824. Min Act: -0.1700
Data Index: 379526 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19