Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4723 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1756. Min Range: -6.1756
Max Act: 6.1756. Min Act: -0.1700
Data Index: 8178307 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1756. Min Range: -6.1756
Max Act: 6.1131. Min Act: -0.1700
Data Index: 4153382 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1756. Min Range: -6.1756
Max Act: 6.0506. Min Act: -0.1700
Data Index: 1983470 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1756. Min Range: -6.1756
Max Act: 6.0506. Min Act: -0.1700
Data Index: 3325419 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1756. Min Range: -6.1756
Max Act: 6.0193. Min Act: -0.1700
Data Index: 8771905 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.9568. Min Act: -0.1700
Data Index: 8564110 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.9568. Min Act: -0.1700
Data Index: 1828937 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.9568. Min Act: -0.1700
Data Index: 2506355 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.9256. Min Act: -0.1700
Data Index: 8805093 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.9256. Min Act: -0.1700
Data Index: 4958668 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.9256. Min Act: -0.1700
Data Index: 8771911 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.8943. Min Act: -0.1700
Data Index: 1443993 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.8943. Min Act: -0.1700
Data Index: 1068137 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.8943. Min Act: -0.1700
Data Index: 1610369 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.9256. Min Act: -0.1700
Data Index: 390200 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.8943. Min Act: -0.1700
Data Index: 6030322 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.8631. Min Act: -0.1700
Data Index: 922093 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.8318. Min Act: -0.1700
Data Index: 6302662 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.8631. Min Act: -0.1700
Data Index: 8443587 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1756. Min Range: -6.1756
Max Act: 5.8631. Min Act: -0.1700
Data Index: 1217934 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19