Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4475 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1502. Min Range: -6.1502
Max Act: 6.1502. Min Act: -0.1700
Data Index: 6324563 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.9940. Min Act: -0.1700
Data Index: 1526998 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.8377. Min Act: -0.1700
Data Index: 2308688 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.7752. Min Act: -0.1700
Data Index: 3110825 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.7127. Min Act: -0.1700
Data Index: 819165 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.7127. Min Act: -0.1700
Data Index: 4391088 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.6815. Min Act: -0.1700
Data Index: 2176817 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.6502. Min Act: -0.1700
Data Index: 504543 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.6190. Min Act: -0.1700
Data Index: 4997739 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.5877. Min Act: -0.1700
Data Index: 3457989 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.6190. Min Act: -0.1700
Data Index: 4325573 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.5877. Min Act: -0.1700
Data Index: 4586571 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.5877. Min Act: -0.1700
Data Index: 5908873 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.5877. Min Act: -0.1700
Data Index: 4463106 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.5565. Min Act: -0.1700
Data Index: 4080271 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.5565. Min Act: -0.1700
Data Index: 8692946 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.5252. Min Act: -0.1700
Data Index: 942317 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.5252. Min Act: -0.1700
Data Index: 4033908 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.4940. Min Act: -0.1700
Data Index: 6983295 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1502. Min Range: -6.1502
Max Act: 5.4627. Min Act: -0.1700
Data Index: 7915023 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19