Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2068 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3283. Min Range: -5.3283
Max Act: 5.3283. Min Act: -0.1700
Data Index: 7507176 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3283. Min Range: -5.3283
Max Act: 5.1096. Min Act: -0.1700
Data Index: 7088565 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3283. Min Range: -5.3283
Max Act: 5.0783. Min Act: -0.1700
Data Index: 8629006 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3283. Min Range: -5.3283
Max Act: 5.0783. Min Act: -0.1700
Data Index: 7632440 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.9846. Min Act: -0.1700
Data Index: 4959668 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.9221. Min Act: -0.1700
Data Index: 5180597 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.9221. Min Act: -0.1700
Data Index: 7796883 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.8908. Min Act: -0.1700
Data Index: 2109096 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.8908. Min Act: -0.1700
Data Index: 6797244 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.8908. Min Act: -0.1700
Data Index: 2547858 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.7971. Min Act: -0.1700
Data Index: 6874240 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.8283. Min Act: -0.1700
Data Index: 3076152 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.8283. Min Act: -0.1700
Data Index: 4908087 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.7971. Min Act: -0.1700
Data Index: 763664 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.7658. Min Act: -0.1700
Data Index: 537507 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.7658. Min Act: -0.1700
Data Index: 6606016 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.7658. Min Act: -0.1700
Data Index: 5279640 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.7658. Min Act: -0.1700
Data Index: 5207566 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.7346. Min Act: -0.1700
Data Index: 2728985 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3283. Min Range: -5.3283
Max Act: 4.7346. Min Act: -0.1700
Data Index: 7825804 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19