Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1039. Min Range: -8.1039
Max Act: 8.1039. Min Act: -0.1700
Data Index: 6616639 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1039. Min Range: -8.1039
Max Act: 7.2289. Min Act: -0.1700
Data Index: 291901 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1039. Min Range: -8.1039
Max Act: 7.0726. Min Act: -0.1700
Data Index: 1425186 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1039. Min Range: -8.1039
Max Act: 7.0414. Min Act: -0.1700
Data Index: 788712 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.9789. Min Act: -0.1700
Data Index: 6936445 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.9476. Min Act: -0.1700
Data Index: 3509979 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.9164. Min Act: -0.1700
Data Index: 4504176 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.9164. Min Act: -0.1700
Data Index: 3132359 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.8539. Min Act: -0.1700
Data Index: 3106691 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.8539. Min Act: -0.1700
Data Index: 5662307 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.8539. Min Act: -0.1700
Data Index: 8345052 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.8539. Min Act: -0.1700
Data Index: 2425545 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.8226. Min Act: -0.1700
Data Index: 3333346 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.8226. Min Act: -0.1700
Data Index: 6350874 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.7601. Min Act: -0.1700
Data Index: 2141126 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.7601. Min Act: -0.1700
Data Index: 2611995 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.7289. Min Act: -0.1700
Data Index: 5108303 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.7289. Min Act: -0.1700
Data Index: 5825395 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.6976. Min Act: -0.1700
Data Index: 2212829 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1039. Min Range: -8.1039
Max Act: 6.6976. Min Act: -0.1700
Data Index: 185984 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19