Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.6492. Min Act: -0.1700
Data Index: 1531448 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.5867. Min Act: -0.1700
Data Index: 1738279 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.5554. Min Act: -0.1700
Data Index: 4345370 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.5242. Min Act: -0.1700
Data Index: 7176456 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.4304. Min Act: -0.1700
Data Index: 7165902 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.4304. Min Act: -0.1700
Data Index: 7217620 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3992. Min Act: -0.1700
Data Index: 2801096 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3679. Min Act: -0.1700
Data Index: 6432819 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3679. Min Act: -0.1700
Data Index: 7037364 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3679. Min Act: -0.1700
Data Index: 8402534 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3679. Min Act: -0.1700
Data Index: 4785852 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3679. Min Act: -0.1700
Data Index: 1865016 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3054. Min Act: -0.1700
Data Index: 647203 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3367. Min Act: -0.1700
Data Index: 786321 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3367. Min Act: -0.1700
Data Index: 1121932 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3054. Min Act: -0.1700
Data Index: 1961920 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3367. Min Act: -0.1700
Data Index: 7208979 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3054. Min Act: -0.1700
Data Index: 2323464 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.3054. Min Act: -0.1700
Data Index: 3474128 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6492. Min Range: -5.6492
Max Act: 5.2742. Min Act: -0.1700
Data Index: 6107007 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19