Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6832. Min Act: -0.1700
Data Index: 5624359 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6511. Min Act: -0.1700
Data Index: 2991751 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6351. Min Act: -0.1700
Data Index: 5827534 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6351. Min Act: -0.1700
Data Index: 8736256 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6351. Min Act: -0.1700
Data Index: 5511625 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6190. Min Act: -0.1700
Data Index: 556422 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6190. Min Act: -0.1700
Data Index: 6711902 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6190. Min Act: -0.1700
Data Index: 2131737 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6190. Min Act: -0.1700
Data Index: 1819438 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6190. Min Act: -0.1700
Data Index: 4513350 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6190. Min Act: -0.1700
Data Index: 5368127 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6029. Min Act: -0.1700
Data Index: 5714693 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6029. Min Act: -0.1700
Data Index: 3031059 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6029. Min Act: -0.1700
Data Index: 5461950 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6029. Min Act: -0.1700
Data Index: 641334 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6029. Min Act: -0.1700
Data Index: 1776049 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.6029. Min Act: -0.1700
Data Index: 6912417 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.5868. Min Act: -0.1700
Data Index: 1878080 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.5868. Min Act: -0.1700
Data Index: 2319278 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6832. Min Range: -2.6832
Max Act: 2.5868. Min Act: -0.1700
Data Index: 4962705 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19