Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0679. Min Range: -4.0679
Max Act: 4.0679. Min Act: -0.1700
Data Index: 1152672 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.9428. Min Act: -0.1700
Data Index: 47414 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8646. Min Act: -0.1700
Data Index: 4127802 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8646. Min Act: -0.1700
Data Index: 1483914 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8334. Min Act: -0.1700
Data Index: 1158579 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8177. Min Act: -0.1700
Data Index: 7010584 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8177. Min Act: -0.1700
Data Index: 2601902 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7865. Min Act: -0.1700
Data Index: 5361892 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8021. Min Act: -0.1700
Data Index: 6955553 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7395. Min Act: -0.1700
Data Index: 2960474 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7708. Min Act: -0.1700
Data Index: 8290917 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7708. Min Act: -0.1700
Data Index: 8155410 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7552. Min Act: -0.1700
Data Index: 8724402 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7552. Min Act: -0.1700
Data Index: 8133939 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7239. Min Act: -0.1700
Data Index: 6649078 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.6926. Min Act: -0.1700
Data Index: 3033262 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.6926. Min Act: -0.1700
Data Index: 4533113 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7239. Min Act: -0.1700
Data Index: 2376360 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.7083. Min Act: -0.1700
Data Index: 6906099 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.6770. Min Act: -0.1700
Data Index: 3551415 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19