Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2457. Min Range: -7.2457
Max Act: 7.2457. Min Act: -0.1700
Data Index: 672307 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2457. Min Range: -7.2457
Max Act: 7.0894. Min Act: -0.1700
Data Index: 1351798 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2457. Min Range: -7.2457
Max Act: 7.0894. Min Act: -0.1700
Data Index: 229880 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2457. Min Range: -7.2457
Max Act: 7.0894. Min Act: -0.1700
Data Index: 1361296 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2457. Min Range: -7.2457
Max Act: 7.0269. Min Act: -0.1700
Data Index: 2243944 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2457. Min Range: -7.2457
Max Act: 7.0582. Min Act: -0.1700
Data Index: 7919127 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.9957. Min Act: -0.1700
Data Index: 3828157 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.9957. Min Act: -0.1700
Data Index: 8153947 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.9644. Min Act: -0.1700
Data Index: 1596357 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.9644. Min Act: -0.1700
Data Index: 5546451 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.9644. Min Act: -0.1700
Data Index: 563684 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.9332. Min Act: -0.1700
Data Index: 6959360 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.9644. Min Act: -0.1700
Data Index: 827889 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.9332. Min Act: -0.1700
Data Index: 1141521 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.9019. Min Act: -0.1700
Data Index: 8365119 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.8707. Min Act: -0.1700
Data Index: 2502930 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.8707. Min Act: -0.1700
Data Index: 8684216 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.8707. Min Act: -0.1700
Data Index: 3268807 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.8394. Min Act: -0.1700
Data Index: 923282 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2457. Min Range: -7.2457
Max Act: 6.8082. Min Act: -0.1700
Data Index: 1117679 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19