Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6190. Min Range: -8.6190
Max Act: 8.6190. Min Act: -0.1700
Data Index: 4986788 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6190. Min Range: -8.6190
Max Act: 8.4940. Min Act: -0.1700
Data Index: 1727293 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6190. Min Range: -8.6190
Max Act: 8.3690. Min Act: -0.1700
Data Index: 3449497 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6190. Min Range: -8.6190
Max Act: 8.2753. Min Act: -0.1700
Data Index: 4043358 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6190. Min Range: -8.6190
Max Act: 8.1503. Min Act: -0.1700
Data Index: 3937713 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6190. Min Range: -8.6190
Max Act: 8.1190. Min Act: -0.1700
Data Index: 6758888 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6190. Min Range: -8.6190
Max Act: 8.0878. Min Act: -0.1700
Data Index: 2197942 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6190. Min Range: -8.6190
Max Act: 8.0878. Min Act: -0.1700
Data Index: 7793188 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6190. Min Range: -8.6190
Max Act: 8.0253. Min Act: -0.1700
Data Index: 1452835 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.9940. Min Act: -0.1700
Data Index: 2556201 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.9315. Min Act: -0.1700
Data Index: 4060071 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.9315. Min Act: -0.1700
Data Index: 6492332 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.9315. Min Act: -0.1700
Data Index: 6612806 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.9003. Min Act: -0.1700
Data Index: 7213656 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.8065. Min Act: -0.1700
Data Index: 5798319 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.8065. Min Act: -0.1700
Data Index: 6622599 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.8065. Min Act: -0.1700
Data Index: 3116184 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.8065. Min Act: -0.1700
Data Index: 1573054 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.7440. Min Act: -0.1700
Data Index: 3254769 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6190. Min Range: -8.6190
Max Act: 7.7440. Min Act: -0.1700
Data Index: 3619380 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19