Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 557 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.8321. Min Act: -0.1700
Data Index: 6996090 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.8321. Min Act: -0.1700
Data Index: 4890379 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7696. Min Act: -0.1700
Data Index: 1731045 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.8008. Min Act: -0.1700
Data Index: 3823673 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7383. Min Act: -0.1700
Data Index: 2476138 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7696. Min Act: -0.1700
Data Index: 172759 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7383. Min Act: -0.1700
Data Index: 3088523 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7383. Min Act: -0.1700
Data Index: 3188523 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7383. Min Act: -0.1700
Data Index: 2091634 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7071. Min Act: -0.1700
Data Index: 7295684 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7071. Min Act: -0.1700
Data Index: 2543319 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3271719 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7071. Min Act: -0.1700
Data Index: 1624943 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3165872 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.7071. Min Act: -0.1700
Data Index: 603253 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.6446. Min Act: -0.1700
Data Index: 525758 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.6446. Min Act: -0.1700
Data Index: 5045591 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.6446. Min Act: -0.1700
Data Index: 4594511 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.6446. Min Act: -0.1700
Data Index: 1769030 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8321. Min Range: -5.8321
Max Act: 5.6758. Min Act: -0.1700
Data Index: 1556902 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19