Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1279 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1488. Min Range: -6.1488
Max Act: 6.1488. Min Act: -0.1700
Data Index: 371243 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1488. Min Range: -6.1488
Max Act: 6.1176. Min Act: -0.1700
Data Index: 127103 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1488. Min Range: -6.1488
Max Act: 6.1176. Min Act: -0.1700
Data Index: 5913192 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1488. Min Range: -6.1488
Max Act: 6.0863. Min Act: -0.1700
Data Index: 12089 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1488. Min Range: -6.1488
Max Act: 6.0551. Min Act: -0.1700
Data Index: 3334405 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1488. Min Range: -6.1488
Max Act: 6.0551. Min Act: -0.1700
Data Index: 5198468 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1488. Min Range: -6.1488
Max Act: 6.0238. Min Act: -0.1700
Data Index: 3776612 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.9926. Min Act: -0.1700
Data Index: 4099327 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.9613. Min Act: -0.1700
Data Index: 2038715 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.9926. Min Act: -0.1700
Data Index: 4519732 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.9926. Min Act: -0.1700
Data Index: 119262 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.9613. Min Act: -0.1700
Data Index: 7697949 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.9613. Min Act: -0.1700
Data Index: 4439857 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.9301. Min Act: -0.1700
Data Index: 3002204 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.8988. Min Act: -0.1700
Data Index: 4247135 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.8363. Min Act: -0.1700
Data Index: 3899266 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.8363. Min Act: -0.1700
Data Index: 4618812 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.8363. Min Act: -0.1700
Data Index: 6056708 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.8051. Min Act: -0.1700
Data Index: 5068458 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1488. Min Range: -6.1488
Max Act: 5.8051. Min Act: -0.1700
Data Index: 1138805 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19