Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2019 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4815. Min Act: -0.1700
Data Index: 456550 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4972. Min Act: -0.1700
Data Index: 5497994 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4972. Min Act: -0.1700
Data Index: 697719 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4658. Min Act: -0.1700
Data Index: 7639413 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4658. Min Act: -0.1700
Data Index: 4450060 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4502. Min Act: -0.1700
Data Index: 6938238 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4502. Min Act: -0.1700
Data Index: 2338840 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4345. Min Act: -0.1700
Data Index: 2938866 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4502. Min Act: -0.1700
Data Index: 8596820 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4345. Min Act: -0.1700
Data Index: 3524497 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4345. Min Act: -0.1700
Data Index: 1583499 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4188. Min Act: -0.1700
Data Index: 3899776 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4188. Min Act: -0.1700
Data Index: 8566120 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4188. Min Act: -0.1700
Data Index: 8183902 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4188. Min Act: -0.1700
Data Index: 1978288 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4188. Min Act: -0.1700
Data Index: 4148994 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4188. Min Act: -0.1700
Data Index: 127605 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4188. Min Act: -0.1700
Data Index: 1885719 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4032. Min Act: -0.1700
Data Index: 2979834 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4972. Min Range: -3.4972
Max Act: 3.4345. Min Act: -0.1700
Data Index: 499306 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19