Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5260 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2071. Min Range: -8.2071
Max Act: 8.2071. Min Act: -0.1700
Data Index: 7340959 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2071. Min Range: -8.2071
Max Act: 8.1446. Min Act: -0.1700
Data Index: 2105734 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.7383. Min Act: -0.1700
Data Index: 6671470 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.6758. Min Act: -0.1700
Data Index: 2915550 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.6446. Min Act: -0.1700
Data Index: 4275454 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.5821. Min Act: -0.1700
Data Index: 2502128 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.5508. Min Act: -0.1700
Data Index: 8237647 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.5196. Min Act: -0.1700
Data Index: 8390923 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.4883. Min Act: -0.1700
Data Index: 2852717 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.4571. Min Act: -0.1700
Data Index: 562200 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.4258. Min Act: -0.1700
Data Index: 5946019 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.4258. Min Act: -0.1700
Data Index: 4642480 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.3946. Min Act: -0.1700
Data Index: 7364313 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.3633. Min Act: -0.1700
Data Index: 3584031 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.3946. Min Act: -0.1700
Data Index: 719917 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.3633. Min Act: -0.1700
Data Index: 7817754 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.3633. Min Act: -0.1700
Data Index: 3324068 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.3633. Min Act: -0.1700
Data Index: 3046579 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.3633. Min Act: -0.1700
Data Index: 4295698 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2071. Min Range: -8.2071
Max Act: 7.3633. Min Act: -0.1700
Data Index: 4705499 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19