Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.7423. Min Act: -0.1700
Data Index: 5721371 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.6798. Min Act: -0.1700
Data Index: 4456623 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.6173. Min Act: -0.1700
Data Index: 3019320 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.5548. Min Act: -0.1700
Data Index: 1687868 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.4298. Min Act: -0.1700
Data Index: 6975339 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.3673. Min Act: -0.1700
Data Index: 4803305 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.3673. Min Act: -0.1700
Data Index: 2731368 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.3673. Min Act: -0.1700
Data Index: 947592 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.3048. Min Act: -0.1700
Data Index: 5541433 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.1798. Min Act: -0.1700
Data Index: 2132373 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.2423. Min Act: -0.1700
Data Index: 965135 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.2423. Min Act: -0.1700
Data Index: 7295551 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.2423. Min Act: -0.1700
Data Index: 4146011 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.1798. Min Act: -0.1700
Data Index: 1687866 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.2423. Min Act: -0.1700
Data Index: 6887268 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.1798. Min Act: -0.1700
Data Index: 926101 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.1798. Min Act: -0.1700
Data Index: 2388526 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.1798. Min Act: -0.1700
Data Index: 3002241 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.1798. Min Act: -0.1700
Data Index: 2992653 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7423. Min Range: -9.7423
Max Act: 9.1173. Min Act: -0.1700
Data Index: 1053845 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19