Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2616 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.4584. Min Act: -0.1700
Data Index: 2054413 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.2709. Min Act: -0.1700
Data Index: 2900594 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.2396. Min Act: -0.1700
Data Index: 3235423 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.1459. Min Act: -0.1700
Data Index: 5977015 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.0834. Min Act: -0.1700
Data Index: 5784478 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.0834. Min Act: -0.1700
Data Index: 5328539 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.0521. Min Act: -0.1700
Data Index: 5846958 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.0521. Min Act: -0.1700
Data Index: 2490682 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.0209. Min Act: -0.1700
Data Index: 6327719 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.0209. Min Act: -0.1700
Data Index: 5621156 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4584. Min Range: -5.4584
Max Act: 5.0209. Min Act: -0.1700
Data Index: 4242379 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4584. Min Range: -5.4584
Max Act: 4.9896. Min Act: -0.1700
Data Index: 7345283 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4584. Min Range: -5.4584
Max Act: 4.9896. Min Act: -0.1700
Data Index: 1366043 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4584. Min Range: -5.4584
Max Act: 4.9896. Min Act: -0.1700
Data Index: 5898888 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4584. Min Range: -5.4584
Max Act: 4.9584. Min Act: -0.1700
Data Index: 7690502 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4584. Min Range: -5.4584
Max Act: 4.9584. Min Act: -0.1700
Data Index: 6522084 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4584. Min Range: -5.4584
Max Act: 4.9584. Min Act: -0.1700
Data Index: 7928844 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4584. Min Range: -5.4584
Max Act: 4.9271. Min Act: -0.1700
Data Index: 1839530 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4584. Min Range: -5.4584
Max Act: 4.9584. Min Act: -0.1700
Data Index: 5615860 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4584. Min Range: -5.4584
Max Act: 4.9271. Min Act: -0.1700
Data Index: 5912273 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19