Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.3330. Min Act: -0.1700
Data Index: 264679 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.2705. Min Act: -0.1700
Data Index: 4839791 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.1767. Min Act: -0.1700
Data Index: 4476010 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.1767. Min Act: -0.1700
Data Index: 2252390 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.1455. Min Act: -0.1700
Data Index: 6572496 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.1142. Min Act: -0.1700
Data Index: 1699707 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.0830. Min Act: -0.1700
Data Index: 3863832 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.1142. Min Act: -0.1700
Data Index: 7178269 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.0830. Min Act: -0.1700
Data Index: 677185 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.0830. Min Act: -0.1700
Data Index: 1205122 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.0830. Min Act: -0.1700
Data Index: 5119058 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3330. Min Range: -6.3330
Max Act: 6.0517. Min Act: -0.1700
Data Index: 6208234 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3330. Min Range: -6.3330
Max Act: 5.9892. Min Act: -0.1700
Data Index: 3382671 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3330. Min Range: -6.3330
Max Act: 5.9892. Min Act: -0.1700
Data Index: 2904033 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3330. Min Range: -6.3330
Max Act: 5.9892. Min Act: -0.1700
Data Index: 3002613 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3330. Min Range: -6.3330
Max Act: 5.9580. Min Act: -0.1700
Data Index: 1395692 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3330. Min Range: -6.3330
Max Act: 5.9267. Min Act: -0.1700
Data Index: 4214434 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3330. Min Range: -6.3330
Max Act: 5.9580. Min Act: -0.1700
Data Index: 1036330 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3330. Min Range: -6.3330
Max Act: 5.9580. Min Act: -0.1700
Data Index: 5272213 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3330. Min Range: -6.3330
Max Act: 5.9267. Min Act: -0.1700
Data Index: 952217 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19