Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6395 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3578. Min Range: -8.3578
Max Act: 8.3578. Min Act: -0.1700
Data Index: 3370147 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3578. Min Range: -8.3578
Max Act: 8.0453. Min Act: -0.1700
Data Index: 8672194 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3578. Min Range: -8.3578
Max Act: 8.0453. Min Act: -0.1700
Data Index: 3672418 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.9828. Min Act: -0.1700
Data Index: 3299977 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.9203. Min Act: -0.1700
Data Index: 3103368 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.8578. Min Act: -0.1700
Data Index: 3777883 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.7953. Min Act: -0.1700
Data Index: 7129234 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.7953. Min Act: -0.1700
Data Index: 4525644 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.7953. Min Act: -0.1700
Data Index: 4395441 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.7328. Min Act: -0.1700
Data Index: 2011804 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.7328. Min Act: -0.1700
Data Index: 7725115 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.7328. Min Act: -0.1700
Data Index: 7021443 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.6703. Min Act: -0.1700
Data Index: 6614495 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.6703. Min Act: -0.1700
Data Index: 676502 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.7015. Min Act: -0.1700
Data Index: 5299225 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.6390. Min Act: -0.1700
Data Index: 6000210 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.6390. Min Act: -0.1700
Data Index: 1262455 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.6703. Min Act: -0.1700
Data Index: 6726326 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.6078. Min Act: -0.1700
Data Index: 1211661 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3578. Min Range: -8.3578
Max Act: 7.6078. Min Act: -0.1700
Data Index: 2902592 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19