Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 647 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.5885. Min Act: -0.1699
Data Index: 7754000 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.5885. Min Act: -0.1700
Data Index: 5278010 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.5573. Min Act: -0.1700
Data Index: 6797957 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.5573. Min Act: -0.1700
Data Index: 1685300 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.5573. Min Act: -0.1700
Data Index: 668491 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.5260. Min Act: -0.1700
Data Index: 5504835 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.5260. Min Act: -0.1700
Data Index: 1935619 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.5260. Min Act: -0.1700
Data Index: 4753335 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.5260. Min Act: -0.1700
Data Index: 7837738 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4948. Min Act: -0.1698
Data Index: 3446804 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4635. Min Act: -0.1700
Data Index: 5445333 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4635. Min Act: -0.1699
Data Index: 1214373 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4948. Min Act: -0.1700
Data Index: 5623268 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4948. Min Act: -0.1700
Data Index: 5724509 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4948. Min Act: -0.1700
Data Index: 3145378 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4948. Min Act: -0.1700
Data Index: 6199392 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4948. Min Act: -0.1700
Data Index: 1045111 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4948. Min Act: -0.1700
Data Index: 60000 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4948. Min Act: -0.1697
Data Index: 4218319 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5885. Min Range: -4.5885
Max Act: 4.4948. Min Act: -0.1700
Data Index: 2155024 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19