Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.9820. Min Act: -0.1700
Data Index: 8317434 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.9507. Min Act: -0.1700
Data Index: 8437939 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.9507. Min Act: -0.1700
Data Index: 4575118 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.9195. Min Act: -0.1700
Data Index: 1315969 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.8882. Min Act: -0.1700
Data Index: 4777760 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.8882. Min Act: -0.1700
Data Index: 4962798 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.8257. Min Act: -0.1700
Data Index: 270675 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7944. Min Act: -0.1700
Data Index: 599768 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7944. Min Act: -0.1700
Data Index: 4877794 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7944. Min Act: -0.1700
Data Index: 1604080 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7944. Min Act: -0.1700
Data Index: 2481228 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7632. Min Act: -0.1700
Data Index: 2065906 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7632. Min Act: -0.1700
Data Index: 2543977 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7319. Min Act: -0.1697
Data Index: 6916141 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7319. Min Act: -0.1659
Data Index: 1120770 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7319. Min Act: -0.1700
Data Index: 7568310 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7319. Min Act: -0.1700
Data Index: 5403720 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7319. Min Act: -0.1700
Data Index: 4437888 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7319. Min Act: -0.1700
Data Index: 5487038 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9820. Min Range: -4.9820
Max Act: 4.7319. Min Act: -0.1700
Data Index: 2220629 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19