Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3240 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1006. Min Range: -10.1006
Max Act: 10.1006. Min Act: -0.1700
Data Index: 7708087 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1006. Min Range: -10.1006
Max Act: 10.0381. Min Act: -0.1700
Data Index: 6515967 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.9131. Min Act: -0.1700
Data Index: 1483704 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.6006. Min Act: -0.1700
Data Index: 848543 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.5381. Min Act: -0.1700
Data Index: 4255820 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.4756. Min Act: -0.1700
Data Index: 6921575 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.4131. Min Act: -0.1700
Data Index: 1302877 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.3506. Min Act: -0.1700
Data Index: 762502 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.2256. Min Act: -0.1700
Data Index: 2784390 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.2881. Min Act: -0.1700
Data Index: 8406111 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.2881. Min Act: -0.1700
Data Index: 8548303 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.2881. Min Act: -0.1700
Data Index: 8079274 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.2881. Min Act: -0.1700
Data Index: 4945433 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.2881. Min Act: -0.1700
Data Index: 201769 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.2881. Min Act: -0.1700
Data Index: 7494614 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.2256. Min Act: -0.1700
Data Index: 5954059 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.2256. Min Act: -0.1700
Data Index: 4240345 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.2256. Min Act: -0.1700
Data Index: 4357903 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.1631. Min Act: -0.1700
Data Index: 2350746 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1006. Min Range: -10.1006
Max Act: 9.1631. Min Act: -0.1700
Data Index: 1520470 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19