Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 897 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.6679. Min Act: -0.1700
Data Index: 1240752 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.6592. Min Act: -0.1700
Data Index: 5306492 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.6069. Min Act: -0.1700
Data Index: 6079826 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.6069. Min Act: -0.1700
Data Index: 2428146 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5894. Min Act: -0.1700
Data Index: 5175498 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5807. Min Act: -0.1700
Data Index: 2971642 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5894. Min Act: -0.1700
Data Index: 6568751 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5807. Min Act: -0.1700
Data Index: 4438062 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5807. Min Act: -0.1700
Data Index: 77219 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5894. Min Act: -0.1700
Data Index: 7672937 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5894. Min Act: -0.1700
Data Index: 1776857 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5894. Min Act: -0.1700
Data Index: 6035540 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5807. Min Act: -0.1698
Data Index: 3292555 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5807. Min Act: -0.1700
Data Index: 6394620 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5632. Min Act: -0.1698
Data Index: 1499587 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5632. Min Act: -0.1699
Data Index: 6674088 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5719. Min Act: -0.1700
Data Index: 185328 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5632. Min Act: -0.1700
Data Index: 7435508 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5544. Min Act: -0.1679
Data Index: 1717805 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6679. Min Range: -1.6679
Max Act: 1.5632. Min Act: -0.1700
Data Index: 6054860 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19