Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1896. Min Range: -7.1896
Max Act: 7.1896. Min Act: -0.1700
Data Index: 6088511 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.9084. Min Act: -0.1700
Data Index: 6044357 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.8771. Min Act: -0.1700
Data Index: 3859097 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.8459. Min Act: -0.1700
Data Index: 1434748 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.7521. Min Act: -0.1700
Data Index: 1432874 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.6584. Min Act: -0.1700
Data Index: 5696574 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.6896. Min Act: -0.1700
Data Index: 7402260 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.7209. Min Act: -0.1700
Data Index: 6276314 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.6896. Min Act: -0.1700
Data Index: 7188430 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.6896. Min Act: -0.1700
Data Index: 7573466 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.6584. Min Act: -0.1700
Data Index: 3138621 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.6584. Min Act: -0.1700
Data Index: 8240492 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.6271. Min Act: -0.1700
Data Index: 3579691 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.6584. Min Act: -0.1700
Data Index: 4285739 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.5959. Min Act: -0.1700
Data Index: 5680209 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.6271. Min Act: -0.1700
Data Index: 6798575 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.5959. Min Act: -0.1700
Data Index: 1955387 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.5959. Min Act: -0.1700
Data Index: 6272832 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.5646. Min Act: -0.1700
Data Index: 6933240 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1896. Min Range: -7.1896
Max Act: 6.6271. Min Act: -0.1700
Data Index: 1506420 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19