Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1508 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.8362. Min Act: -0.1700
Data Index: 3158430 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.8362. Min Act: -0.1700
Data Index: 5567273 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.8362. Min Act: -0.1700
Data Index: 2479720 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7424. Min Act: -0.1700
Data Index: 352894 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6798. Min Act: -0.1700
Data Index: 7098186 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6485. Min Act: -0.1700
Data Index: 3330780 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6172. Min Act: -0.1700
Data Index: 921433 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6172. Min Act: -0.1700
Data Index: 526974 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6016. Min Act: -0.1700
Data Index: 8352074 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6172. Min Act: -0.1700
Data Index: 3351978 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5703. Min Act: -0.1700
Data Index: 7194585 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6016. Min Act: -0.1700
Data Index: 8747293 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5859. Min Act: -0.1700
Data Index: 7403715 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5703. Min Act: -0.1700
Data Index: 3826509 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5703. Min Act: -0.1700
Data Index: 1803847 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5703. Min Act: -0.1700
Data Index: 4901095 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5546. Min Act: -0.1700
Data Index: 4928134 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5703. Min Act: -0.1700
Data Index: 1192899 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5703. Min Act: -0.1700
Data Index: 4565583 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.5233. Min Act: -0.1700
Data Index: 1263539 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19