Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3571 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.3421. Min Act: -0.1700
Data Index: 8344011 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.2268. Min Act: -0.1700
Data Index: 2937312 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.2103. Min Act: -0.1700
Data Index: 4776894 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.1270. Min Act: -0.1700
Data Index: 5384577 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.1103. Min Act: -0.1700
Data Index: 3795853 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0936. Min Act: -0.1700
Data Index: 6625168 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0936. Min Act: -0.1699
Data Index: 4316215 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0936. Min Act: -0.1700
Data Index: 8688596 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.1103. Min Act: -0.1699
Data Index: 6530256 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0768. Min Act: -0.1700
Data Index: 721686 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0768. Min Act: -0.1700
Data Index: 7759820 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0600. Min Act: -0.1700
Data Index: 6252073 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0432. Min Act: -0.1698
Data Index: 6365631 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0432. Min Act: -0.1700
Data Index: 8475438 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0600. Min Act: -0.1700
Data Index: 58673 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0264. Min Act: -0.1700
Data Index: 3504382 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0432. Min Act: -0.1694
Data Index: 7554581 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0600. Min Act: -0.1700
Data Index: 8213763 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0600. Min Act: -0.1699
Data Index: 7684013 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3421. Min Range: -2.3421
Max Act: 2.0264. Min Act: -0.1700
Data Index: 5125099 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19