Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2863 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2078. Min Range: -4.2078
Max Act: 4.2078. Min Act: -0.1700
Data Index: 7158730 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2078. Min Range: -4.2078
Max Act: 4.1765. Min Act: -0.1700
Data Index: 7003372 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2078. Min Range: -4.2078
Max Act: 4.0202. Min Act: -0.1700
Data Index: 7040330 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.9733. Min Act: -0.1700
Data Index: 7917181 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.9421. Min Act: -0.1700
Data Index: 5396095 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.9421. Min Act: -0.1700
Data Index: 1294596 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.9108. Min Act: -0.1700
Data Index: 5339516 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8952. Min Act: -0.1700
Data Index: 4777814 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8796. Min Act: -0.1700
Data Index: 6844100 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8796. Min Act: -0.1700
Data Index: 4432390 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8796. Min Act: -0.1700
Data Index: 6113968 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8639. Min Act: -0.1700
Data Index: 6932318 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8327. Min Act: -0.1700
Data Index: 3265626 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8170. Min Act: -0.1700
Data Index: 8308034 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8327. Min Act: -0.1700
Data Index: 3900516 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8170. Min Act: -0.1700
Data Index: 7708087 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8014. Min Act: -0.1700
Data Index: 564170 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8014. Min Act: -0.1700
Data Index: 1384934 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.7857. Min Act: -0.1700
Data Index: 1632852 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8014. Min Act: -0.1700
Data Index: 7384466 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19