Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4984 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.9362. Min Act: -0.1700
Data Index: 5619446 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.9050. Min Act: -0.1700
Data Index: 6213337 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.9050. Min Act: -0.1700
Data Index: 5619444 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.9050. Min Act: -0.1700
Data Index: 6448292 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.8737. Min Act: -0.1700
Data Index: 5490076 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.8737. Min Act: -0.1700
Data Index: 6448290 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.8425. Min Act: -0.1700
Data Index: 2939877 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.8425. Min Act: -0.1700
Data Index: 4106652 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.7800. Min Act: -0.1700
Data Index: 5490074 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.7487. Min Act: -0.1700
Data Index: 6052447 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.7487. Min Act: -0.1700
Data Index: 5619448 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.7487. Min Act: -0.1700
Data Index: 584026 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.7487. Min Act: -0.1700
Data Index: 2865583 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.7175. Min Act: -0.1700
Data Index: 5047658 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.6862. Min Act: -0.1700
Data Index: 584024 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.6862. Min Act: -0.1700
Data Index: 5957660 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.7175. Min Act: -0.1700
Data Index: 6371126 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.6862. Min Act: -0.1700
Data Index: 3844532 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.6862. Min Act: -0.1700
Data Index: 737277 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9362. Min Range: -5.9362
Max Act: 5.6862. Min Act: -0.1700
Data Index: 7041642 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19