Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2253. Min Range: -9.2253
Max Act: 9.2253. Min Act: -0.1700
Data Index: 3775636 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2253. Min Range: -9.2253
Max Act: 9.1628. Min Act: -0.1700
Data Index: 672281 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.9753. Min Act: -0.1700
Data Index: 8337596 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.9753. Min Act: -0.1700
Data Index: 1074766 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.9128. Min Act: -0.1700
Data Index: 3761992 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.9753. Min Act: -0.1700
Data Index: 645779 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.9128. Min Act: -0.1700
Data Index: 4903779 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.8503. Min Act: -0.1700
Data Index: 7207876 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.8503. Min Act: -0.1700
Data Index: 3968990 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.9128. Min Act: -0.1700
Data Index: 4872294 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.7878. Min Act: -0.1700
Data Index: 7551082 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.7878. Min Act: -0.1700
Data Index: 1942333 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.7878. Min Act: -0.1700
Data Index: 781673 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.7253. Min Act: -0.1700
Data Index: 5910121 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.7253. Min Act: -0.1700
Data Index: 757319 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.7878. Min Act: -0.1700
Data Index: 7576767 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.7878. Min Act: -0.1700
Data Index: 1900795 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.7253. Min Act: -0.1700
Data Index: 5175522 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.6628. Min Act: -0.1700
Data Index: 7042994 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2253. Min Range: -9.2253
Max Act: 8.7878. Min Act: -0.1700
Data Index: 3207329 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19