Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5442 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 1713574 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 2071516 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 8511157 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 8312192 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 1585247 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 108786 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 6191372 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.4290. Min Act: -0.1700
Data Index: 3093712 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3977. Min Act: -0.1700
Data Index: 7858795 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3977. Min Act: -0.1700
Data Index: 2285968 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3977. Min Act: -0.1700
Data Index: 2673299 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 3133009 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 4295751 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 7956946 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 8183388 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 3451042 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 2633543 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 2067040 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 6146405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4290. Min Range: -4.4290
Max Act: 4.3665. Min Act: -0.1700
Data Index: 2122639 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19