Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.9427. Min Act: -0.1700
Data Index: 3892251 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.9427. Min Act: -0.1700
Data Index: 5463237 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.9115. Min Act: -0.1700
Data Index: 3367681 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.8490. Min Act: -0.1700
Data Index: 3739621 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.8490. Min Act: -0.1700
Data Index: 4308022 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.8177. Min Act: -0.1700
Data Index: 4660022 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.8490. Min Act: -0.1700
Data Index: 2732783 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.7865. Min Act: -0.1700
Data Index: 1797255 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.8177. Min Act: -0.1700
Data Index: 8057961 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.7865. Min Act: -0.1700
Data Index: 3491514 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.8177. Min Act: -0.1700
Data Index: 2581375 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.7552. Min Act: -0.1700
Data Index: 7752140 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.7552. Min Act: -0.1700
Data Index: 5585059 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.7552. Min Act: -0.1700
Data Index: 7733627 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.7552. Min Act: -0.1700
Data Index: 4223194 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.6927. Min Act: -0.1700
Data Index: 2171164 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.6927. Min Act: -0.1700
Data Index: 5851632 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.7865. Min Act: -0.1700
Data Index: 965127 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.7552. Min Act: -0.1700
Data Index: 8366504 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9427. Min Range: -5.9427
Max Act: 5.7240. Min Act: -0.1700
Data Index: 6066376 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19