Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.9466. Min Act: -0.1700
Data Index: 28373 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.9154. Min Act: -0.1700
Data Index: 7068646 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.7591. Min Act: -0.1700
Data Index: 4098582 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.6029. Min Act: -0.1700
Data Index: 1432542 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.5404. Min Act: -0.1700
Data Index: 5651671 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.4779. Min Act: -0.1700
Data Index: 4777504 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.4779. Min Act: -0.1700
Data Index: 5900487 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.3841. Min Act: -0.1700
Data Index: 6549723 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.2904. Min Act: -0.1700
Data Index: 6433703 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.2591. Min Act: -0.1700
Data Index: 8603418 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.2904. Min Act: -0.1700
Data Index: 6190050 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.2591. Min Act: -0.1700
Data Index: 4708173 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.1654. Min Act: -0.1700
Data Index: 4064331 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.2279. Min Act: -0.1700
Data Index: 5867307 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.1966. Min Act: -0.1700
Data Index: 4969584 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.1966. Min Act: -0.1700
Data Index: 2215868 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.1654. Min Act: -0.1700
Data Index: 3165065 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.1966. Min Act: -0.1700
Data Index: 8142140 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.1966. Min Act: -0.1700
Data Index: 5215141 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9466. Min Range: -5.9466
Max Act: 5.1966. Min Act: -0.1700
Data Index: 4439358 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19