Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3693 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.3747. Min Range: -10.3747
Max Act: 10.3747. Min Act: -0.1700
Data Index: 6673408 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3747. Min Range: -10.3747
Max Act: 10.0622. Min Act: -0.1700
Data Index: 2399419 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.9372. Min Act: -0.1700
Data Index: 6579999 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.8122. Min Act: -0.1700
Data Index: 7169069 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.8122. Min Act: -0.1700
Data Index: 7810723 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.6247. Min Act: -0.1700
Data Index: 3562064 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.6247. Min Act: -0.1700
Data Index: 5746620 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.4997. Min Act: -0.1700
Data Index: 1808737 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.4997. Min Act: -0.1700
Data Index: 5227194 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.3747. Min Act: -0.1700
Data Index: 2333145 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.3122. Min Act: -0.1700
Data Index: 6897012 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.3747. Min Act: -0.1700
Data Index: 174915 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.4372. Min Act: -0.1700
Data Index: 8735691 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.3122. Min Act: -0.1700
Data Index: 5319186 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.3122. Min Act: -0.1700
Data Index: 8050688 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.2497. Min Act: -0.1700
Data Index: 8416116 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.1872. Min Act: -0.1700
Data Index: 5877642 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.0622. Min Act: -0.1700
Data Index: 169166 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.1247. Min Act: -0.1700
Data Index: 5448066 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3747. Min Range: -10.3747
Max Act: 9.1247. Min Act: -0.1700
Data Index: 3409141 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19