Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5393 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.8051. Min Act: -0.1700
Data Index: 1759840 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.8051. Min Act: -0.1700
Data Index: 4824830 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.7426. Min Act: -0.1700
Data Index: 7472668 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.6489. Min Act: -0.1700
Data Index: 4674368 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.6176. Min Act: -0.1700
Data Index: 8523737 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.5551. Min Act: -0.1700
Data Index: 7321525 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.5551. Min Act: -0.1700
Data Index: 2847098 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.5551. Min Act: -0.1700
Data Index: 818513 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.5239. Min Act: -0.1700
Data Index: 7611937 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.4926. Min Act: -0.1700
Data Index: 8827996 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.4614. Min Act: -0.1700
Data Index: 1539078 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.4614. Min Act: -0.1700
Data Index: 6826314 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.4614. Min Act: -0.1700
Data Index: 3987492 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.4301. Min Act: -0.1700
Data Index: 2673980 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.4301. Min Act: -0.1700
Data Index: 695611 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.4301. Min Act: -0.1700
Data Index: 2923936 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.4614. Min Act: -0.1700
Data Index: 8125490 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.3989. Min Act: -0.1700
Data Index: 5899844 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.3676. Min Act: -0.1700
Data Index: 8229648 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8051. Min Range: -5.8051
Max Act: 5.3989. Min Act: -0.1700
Data Index: 6981117 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19