Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1354 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.3779. Min Act: -0.1700
Data Index: 5489875 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2529. Min Act: -0.1700
Data Index: 3656542 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2529. Min Act: -0.1700
Data Index: 712516 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2529. Min Act: -0.1700
Data Index: 2492784 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1904. Min Act: -0.1700
Data Index: 6120078 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2217. Min Act: -0.1700
Data Index: 1031979 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2217. Min Act: -0.1700
Data Index: 4344027 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1904. Min Act: -0.1700
Data Index: 7156211 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1592. Min Act: -0.1700
Data Index: 882354 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1592. Min Act: -0.1700
Data Index: 1006815 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1592. Min Act: -0.1700
Data Index: 1936362 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1592. Min Act: -0.1700
Data Index: 1419934 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1592. Min Act: -0.1700
Data Index: 526437 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1592. Min Act: -0.1700
Data Index: 1471010 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1279. Min Act: -0.1700
Data Index: 1497651 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1279. Min Act: -0.1700
Data Index: 5127660 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1279. Min Act: -0.1700
Data Index: 5773269 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1279. Min Act: -0.1700
Data Index: 4939260 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.0967. Min Act: -0.1700
Data Index: 2215807 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.1279. Min Act: -0.1700
Data Index: 6686222 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19