Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.7481. Min Act: -0.1700
Data Index: 7241005 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.6544. Min Act: -0.1700
Data Index: 6250556 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.5294. Min Act: -0.1700
Data Index: 1404917 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.2481. Min Act: -0.1700
Data Index: 7356703 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.3106. Min Act: -0.1700
Data Index: 5378011 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.2481. Min Act: -0.1700
Data Index: 6577908 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.2481. Min Act: -0.1700
Data Index: 1751058 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.2481. Min Act: -0.1700
Data Index: 685872 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.2169. Min Act: -0.1700
Data Index: 3487008 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.1544. Min Act: -0.1700
Data Index: 2955608 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.1544. Min Act: -0.1700
Data Index: 6665879 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.1544. Min Act: -0.1700
Data Index: 2016925 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.0919. Min Act: -0.1700
Data Index: 5517367 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.0919. Min Act: -0.1700
Data Index: 6814353 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.0919. Min Act: -0.1700
Data Index: 7758350 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.0919. Min Act: -0.1700
Data Index: 324968 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.0606. Min Act: -0.1700
Data Index: 2814987 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.0606. Min Act: -0.1700
Data Index: 7338990 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7481. Min Range: -7.7481
Max Act: 7.0606. Min Act: -0.1700
Data Index: 6908403 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7481. Min Range: -7.7481
Max Act: 6.9669. Min Act: -0.1700
Data Index: 1617282 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19