Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1488. Min Range: -5.1488
Max Act: 5.1488. Min Act: -0.1700
Data Index: 6010238 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1488. Min Range: -5.1488
Max Act: 5.0551. Min Act: -0.1700
Data Index: 2986402 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.9926. Min Act: -0.1700
Data Index: 6066138 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.9926. Min Act: -0.1700
Data Index: 2809632 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.9926. Min Act: -0.1700
Data Index: 8723193 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.9613. Min Act: -0.1700
Data Index: 615697 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.8363. Min Act: -0.1700
Data Index: 1603903 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.8363. Min Act: -0.1700
Data Index: 682646 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.8051. Min Act: -0.1700
Data Index: 6101977 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.8051. Min Act: -0.1700
Data Index: 8550088 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.7738. Min Act: -0.1700
Data Index: 4277112 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.7426. Min Act: -0.1700
Data Index: 6554514 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.7426. Min Act: -0.1700
Data Index: 1172829 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.7426. Min Act: -0.1700
Data Index: 1524149 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.7113. Min Act: -0.1700
Data Index: 8560220 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.6801. Min Act: -0.1700
Data Index: 1004369 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.6488. Min Act: -0.1700
Data Index: 128367 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.6176. Min Act: -0.1700
Data Index: 2678549 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.6176. Min Act: -0.1700
Data Index: 3065320 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1488. Min Range: -5.1488
Max Act: 4.6176. Min Act: -0.1700
Data Index: 5056975 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19