Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.9791. Min Act: -0.1700
Data Index: 757817 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.9166. Min Act: -0.1700
Data Index: 5776454 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.8541. Min Act: -0.1700
Data Index: 1553368 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.8228. Min Act: -0.1700
Data Index: 7648504 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.7916. Min Act: -0.1700
Data Index: 5203544 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.7291. Min Act: -0.1700
Data Index: 1442661 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6978. Min Act: -0.1700
Data Index: 3632290 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6666. Min Act: -0.1700
Data Index: 2798309 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6353. Min Act: -0.1700
Data Index: 693152 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6353. Min Act: -0.1700
Data Index: 4020070 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6353. Min Act: -0.1700
Data Index: 5206637 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6041. Min Act: -0.1700
Data Index: 3345672 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6041. Min Act: -0.1700
Data Index: 1216298 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6041. Min Act: -0.1700
Data Index: 7531821 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6353. Min Act: -0.1700
Data Index: 5043183 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6041. Min Act: -0.1700
Data Index: 2695827 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.6353. Min Act: -0.1700
Data Index: 3149846 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.5728. Min Act: -0.1700
Data Index: 4950267 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.5728. Min Act: -0.1700
Data Index: 2756121 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9791. Min Range: -4.9791
Max Act: 4.5416. Min Act: -0.1700
Data Index: 254203 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19