Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4229 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4859. Min Range: -8.4859
Max Act: 8.4859. Min Act: -0.1700
Data Index: 2769780 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.9859. Min Act: -0.1700
Data Index: 4011940 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.7359. Min Act: -0.1700
Data Index: 3750441 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.7359. Min Act: -0.1700
Data Index: 381267 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.7359. Min Act: -0.1700
Data Index: 5719132 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.6422. Min Act: -0.1700
Data Index: 7918227 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.6422. Min Act: -0.1700
Data Index: 2082888 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.6422. Min Act: -0.1700
Data Index: 987579 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.5484. Min Act: -0.1700
Data Index: 7272718 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.5172. Min Act: -0.1700
Data Index: 1846226 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.5172. Min Act: -0.1700
Data Index: 8731591 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.5172. Min Act: -0.1700
Data Index: 1774227 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.4859. Min Act: -0.1700
Data Index: 1872589 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.4234. Min Act: -0.1700
Data Index: 776059 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.4234. Min Act: -0.1700
Data Index: 3733873 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.3922. Min Act: -0.1700
Data Index: 1420004 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.3922. Min Act: -0.1700
Data Index: 3893266 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.3922. Min Act: -0.1700
Data Index: 951589 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.3609. Min Act: -0.1700
Data Index: 6702510 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4859. Min Range: -8.4859
Max Act: 7.3609. Min Act: -0.1700
Data Index: 8381465 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19