Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.6639. Min Act: -0.1700
Data Index: 2734922 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.5767. Min Act: -0.1700
Data Index: 3574183 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.5592. Min Act: -0.1700
Data Index: 3287051 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.5153. Min Act: -0.1700
Data Index: 2523012 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4802. Min Act: -0.1700
Data Index: 2827247 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.5066. Min Act: -0.1700
Data Index: 2169499 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4539. Min Act: -0.1700
Data Index: 7735542 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4802. Min Act: -0.1700
Data Index: 4390832 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4626. Min Act: -0.1700
Data Index: 2523011 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4539. Min Act: -0.1700
Data Index: 5550041 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4451. Min Act: -0.1700
Data Index: 2961493 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4626. Min Act: -0.1700
Data Index: 6380083 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4539. Min Act: -0.1700
Data Index: 4341935 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4714. Min Act: -0.1700
Data Index: 3481634 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4363. Min Act: -0.1700
Data Index: 6218511 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4363. Min Act: -0.1700
Data Index: 2800343 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4539. Min Act: -0.1700
Data Index: 4921410 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4363. Min Act: -0.1700
Data Index: 6225492 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4186. Min Act: -0.1700
Data Index: 6298438 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6639. Min Range: -1.6639
Max Act: 1.4275. Min Act: -0.1700
Data Index: 4726605 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19