Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.9968. Min Act: -0.1700
Data Index: 452716 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.9343. Min Act: -0.1700
Data Index: 2524873 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.8718. Min Act: -0.1700
Data Index: 1729949 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.8093. Min Act: -0.1700
Data Index: 4755751 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.7468. Min Act: -0.1700
Data Index: 5100960 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.7468. Min Act: -0.1700
Data Index: 4008660 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.7468. Min Act: -0.1700
Data Index: 195851 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.6843. Min Act: -0.1700
Data Index: 4008658 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.6218. Min Act: -0.1700
Data Index: 195850 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.6218. Min Act: -0.1700
Data Index: 4755760 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.6218. Min Act: -0.1700
Data Index: 3402419 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.6218. Min Act: -0.1700
Data Index: 3833273 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.5593. Min Act: -0.1700
Data Index: 95656 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.5593. Min Act: -0.1700
Data Index: 2464191 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.5593. Min Act: -0.1700
Data Index: 4755759 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.5593. Min Act: -0.1700
Data Index: 373780 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.5593. Min Act: -0.1700
Data Index: 5997575 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.4343. Min Act: -0.1700
Data Index: 728703 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.4968. Min Act: -0.1700
Data Index: 4936146 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9968. Min Range: -8.9968
Max Act: 8.4968. Min Act: -0.1700
Data Index: 874767 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19