Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4134 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.7640. Min Act: -0.1700
Data Index: 313682 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.4203. Min Act: -0.1700
Data Index: 636089 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.3265. Min Act: -0.1700
Data Index: 5693839 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.2953. Min Act: -0.1700
Data Index: 24671 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.2953. Min Act: -0.1700
Data Index: 1327008 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.2640. Min Act: -0.1700
Data Index: 412954 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.2640. Min Act: -0.1700
Data Index: 5738698 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.2015. Min Act: -0.1700
Data Index: 1218945 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1703. Min Act: -0.1700
Data Index: 8722002 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1703. Min Act: -0.1700
Data Index: 4605916 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1703. Min Act: -0.1700
Data Index: 1052539 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1703. Min Act: -0.1700
Data Index: 188276 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1703. Min Act: -0.1700
Data Index: 494511 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1703. Min Act: -0.1700
Data Index: 2645385 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1703. Min Act: -0.1700
Data Index: 5146132 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1390. Min Act: -0.1700
Data Index: 4080600 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1390. Min Act: -0.1700
Data Index: 2877845 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1390. Min Act: -0.1700
Data Index: 6260192 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1390. Min Act: -0.1700
Data Index: 3024963 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7640. Min Range: -6.7640
Max Act: 6.1390. Min Act: -0.1700
Data Index: 8338013 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19