Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2776 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.4738. Min Act: -0.1700
Data Index: 6036463 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.2863. Min Act: -0.1700
Data Index: 5019480 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.3175. Min Act: -0.1700
Data Index: 6151515 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.2863. Min Act: -0.1700
Data Index: 6122276 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.2238. Min Act: -0.1700
Data Index: 1751685 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.1925. Min Act: -0.1700
Data Index: 4699015 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.1925. Min Act: -0.1700
Data Index: 7381658 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.1925. Min Act: -0.1700
Data Index: 3281318 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.1613. Min Act: -0.1700
Data Index: 7743683 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.1613. Min Act: -0.1700
Data Index: 3700621 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.0675. Min Act: -0.1700
Data Index: 1096677 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.0675. Min Act: -0.1700
Data Index: 6719928 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.0363. Min Act: -0.1700
Data Index: 5928177 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.0675. Min Act: -0.1700
Data Index: 6001545 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.0363. Min Act: -0.1700
Data Index: 1218322 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.0363. Min Act: -0.1700
Data Index: 8659786 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.0050. Min Act: -0.1700
Data Index: 6736069 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.0050. Min Act: -0.1700
Data Index: 5003785 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.0050. Min Act: -0.1700
Data Index: 5988214 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4738. Min Range: -7.4738
Max Act: 7.0050. Min Act: -0.1700
Data Index: 1337227 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19