Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2253. Min Range: -7.2253
Max Act: 7.2253. Min Act: -0.1700
Data Index: 7393420 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2253. Min Range: -7.2253
Max Act: 7.1003. Min Act: -0.1700
Data Index: 1694836 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2253. Min Range: -7.2253
Max Act: 7.1003. Min Act: -0.1700
Data Index: 1694837 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2253. Min Range: -7.2253
Max Act: 7.1003. Min Act: -0.1700
Data Index: 2694338 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2253. Min Range: -7.2253
Max Act: 7.0691. Min Act: -0.1700
Data Index: 6174366 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2253. Min Range: -7.2253
Max Act: 7.0066. Min Act: -0.1700
Data Index: 2324770 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2253. Min Range: -7.2253
Max Act: 7.0066. Min Act: -0.1700
Data Index: 5813354 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2253. Min Range: -7.2253
Max Act: 7.0378. Min Act: -0.1700
Data Index: 2986799 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2253. Min Range: -7.2253
Max Act: 7.0378. Min Act: -0.1700
Data Index: 3992259 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.9753. Min Act: -0.1700
Data Index: 6206307 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.9753. Min Act: -0.1700
Data Index: 1594112 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.9441. Min Act: -0.1700
Data Index: 2597053 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.9441. Min Act: -0.1700
Data Index: 6719303 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.9441. Min Act: -0.1700
Data Index: 1934417 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.9128. Min Act: -0.1700
Data Index: 7390899 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.8503. Min Act: -0.1700
Data Index: 8819323 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.8503. Min Act: -0.1700
Data Index: 4319633 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.8191. Min Act: -0.1700
Data Index: 4713456 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.8191. Min Act: -0.1700
Data Index: 312321 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2253. Min Range: -7.2253
Max Act: 6.8191. Min Act: -0.1700
Data Index: 586715 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19