Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4427. Min Range: -8.4427
Max Act: 8.4427. Min Act: -0.1700
Data Index: 6576374 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4427. Min Range: -8.4427
Max Act: 7.2552. Min Act: -0.1700
Data Index: 8068647 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4427. Min Range: -8.4427
Max Act: 7.0990. Min Act: -0.1700
Data Index: 8252747 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4427. Min Range: -8.4427
Max Act: 7.0677. Min Act: -0.1700
Data Index: 5067760 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.9427. Min Act: -0.1700
Data Index: 2627477 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.9115. Min Act: -0.1700
Data Index: 1061588 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.8802. Min Act: -0.1700
Data Index: 8817800 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.8177. Min Act: -0.1700
Data Index: 2698638 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.7552. Min Act: -0.1700
Data Index: 4160630 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.7240. Min Act: -0.1700
Data Index: 692214 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.7552. Min Act: -0.1700
Data Index: 8196714 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.6927. Min Act: -0.1700
Data Index: 379908 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.6615. Min Act: -0.1700
Data Index: 6542715 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.6615. Min Act: -0.1700
Data Index: 3170211 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.5990. Min Act: -0.1700
Data Index: 4281338 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.6615. Min Act: -0.1700
Data Index: 455651 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.6302. Min Act: -0.1700
Data Index: 6514910 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.6302. Min Act: -0.1700
Data Index: 1637214 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.6302. Min Act: -0.1700
Data Index: 2026454 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4427. Min Range: -8.4427
Max Act: 6.6302. Min Act: -0.1700
Data Index: 802614 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19