Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1777 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.7169. Min Act: -0.1700
Data Index: 5466350 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.6544. Min Act: -0.1700
Data Index: 8612378 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.6544. Min Act: -0.1700
Data Index: 7560106 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.6232. Min Act: -0.1700
Data Index: 3115208 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.5607. Min Act: -0.1700
Data Index: 1384788 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.5607. Min Act: -0.1700
Data Index: 2741880 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.5294. Min Act: -0.1700
Data Index: 7344523 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.5294. Min Act: -0.1700
Data Index: 1417990 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4669. Min Act: -0.1700
Data Index: 2970192 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4357. Min Act: -0.1700
Data Index: 3697329 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4357. Min Act: -0.1700
Data Index: 8586595 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4357. Min Act: -0.1700
Data Index: 5004068 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.4044. Min Act: -0.1700
Data Index: 5284652 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.3419. Min Act: -0.1700
Data Index: 7425918 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.3732. Min Act: -0.1700
Data Index: 7398788 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.3732. Min Act: -0.1700
Data Index: 7377577 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.3419. Min Act: -0.1700
Data Index: 2854032 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.2794. Min Act: -0.1700
Data Index: 494596 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.2794. Min Act: -0.1700
Data Index: 4804706 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7169. Min Range: -5.7169
Max Act: 5.2482. Min Act: -0.1700
Data Index: 3560342 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19