Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.6496. Min Act: -0.1700
Data Index: 718406 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.6184. Min Act: -0.1700
Data Index: 8794882 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.5871. Min Act: -0.1700
Data Index: 4222844 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.3371. Min Act: -0.1700
Data Index: 4202658 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2746. Min Act: -0.1700
Data Index: 7279830 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2746. Min Act: -0.1700
Data Index: 2553030 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2746. Min Act: -0.1700
Data Index: 2819942 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2434. Min Act: -0.1700
Data Index: 6956076 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2434. Min Act: -0.1700
Data Index: 5003693 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2121. Min Act: -0.1700
Data Index: 1421585 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2121. Min Act: -0.1700
Data Index: 5080626 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2121. Min Act: -0.1700
Data Index: 3425070 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2121. Min Act: -0.1700
Data Index: 2206210 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2121. Min Act: -0.1700
Data Index: 652552 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1809. Min Act: -0.1700
Data Index: 5893281 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1809. Min Act: -0.1700
Data Index: 3594901 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1496. Min Act: -0.1700
Data Index: 8164423 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1809. Min Act: -0.1700
Data Index: 67532 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1184. Min Act: -0.1700
Data Index: 4130775 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1496. Min Act: -0.1700
Data Index: 7420505 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19