Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.1957. Min Act: -0.1700
Data Index: 1728349 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1957. Min Range: -3.1957
Max Act: 3.0223. Min Act: -0.1700
Data Index: 8751120 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.9749. Min Act: -0.1700
Data Index: 6118656 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.9749. Min Act: -0.1700
Data Index: 2001889 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.9591. Min Act: -0.1700
Data Index: 715042 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.9432. Min Act: -0.1700
Data Index: 4718990 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.9274. Min Act: -0.1700
Data Index: 215002 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.9274. Min Act: -0.1700
Data Index: 1078559 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.9432. Min Act: -0.1700
Data Index: 7595283 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.9274. Min Act: -0.1700
Data Index: 6023749 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.9116. Min Act: -0.1700
Data Index: 5860023 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.9116. Min Act: -0.1700
Data Index: 451157 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.8957. Min Act: -0.1700
Data Index: 1159527 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.8957. Min Act: -0.1700
Data Index: 8527298 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.8957. Min Act: -0.1700
Data Index: 6274708 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.8957. Min Act: -0.1700
Data Index: 4327147 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.8798. Min Act: -0.1700
Data Index: 3100863 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.8798. Min Act: -0.1700
Data Index: 8113371 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.8798. Min Act: -0.1700
Data Index: 2477900 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1957. Min Range: -3.1957
Max Act: 2.8640. Min Act: -0.1700
Data Index: 180640 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19