Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4486 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.4744. Min Act: -0.1700
Data Index: 353817 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.2391. Min Act: -0.1700
Data Index: 6618483 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.1919. Min Act: -0.1700
Data Index: 7528419 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.1605. Min Act: -0.1700
Data Index: 8273414 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.1605. Min Act: -0.1700
Data Index: 6899658 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.1132. Min Act: -0.1700
Data Index: 6278273 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0817. Min Act: -0.1700
Data Index: 2875234 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0817. Min Act: -0.1700
Data Index: 8167539 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0659. Min Act: -0.1700
Data Index: 6849255 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0659. Min Act: -0.1700
Data Index: 3408074 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0501. Min Act: -0.1700
Data Index: 8688775 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0501. Min Act: -0.1700
Data Index: 4906709 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0501. Min Act: -0.1700
Data Index: 1178820 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0344. Min Act: -0.1700
Data Index: 6078728 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0501. Min Act: -0.1700
Data Index: 783950 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0501. Min Act: -0.1700
Data Index: 5495554 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0344. Min Act: -0.1700
Data Index: 1263712 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0344. Min Act: -0.1700
Data Index: 154534 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0344. Min Act: -0.1700
Data Index: 6124435 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4744. Min Range: -3.4744
Max Act: 3.0344. Min Act: -0.1700
Data Index: 7702141 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19