Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3234 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0373. Min Range: -6.0373
Max Act: 6.0373. Min Act: -0.1700
Data Index: 478657 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0373. Min Range: -6.0373
Max Act: 6.0061. Min Act: -0.1700
Data Index: 857157 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.9748. Min Act: -0.1700
Data Index: 493051 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.9436. Min Act: -0.1700
Data Index: 1421658 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.8811. Min Act: -0.1700
Data Index: 7282453 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.8811. Min Act: -0.1700
Data Index: 4247116 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.8498. Min Act: -0.1700
Data Index: 4659139 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.8498. Min Act: -0.1700
Data Index: 2577517 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.8186. Min Act: -0.1700
Data Index: 857158 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.8186. Min Act: -0.1700
Data Index: 6647551 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.8186. Min Act: -0.1700
Data Index: 2775356 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.7873. Min Act: -0.1700
Data Index: 4990917 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.7873. Min Act: -0.1700
Data Index: 7677260 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.7561. Min Act: -0.1700
Data Index: 1953969 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.7561. Min Act: -0.1700
Data Index: 6899091 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.7248. Min Act: -0.1700
Data Index: 93079 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.7561. Min Act: -0.1700
Data Index: 478658 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.6623. Min Act: -0.1700
Data Index: 2754917 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.6623. Min Act: -0.1700
Data Index: 1530797 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0373. Min Range: -6.0373
Max Act: 5.6311. Min Act: -0.1700
Data Index: 3623850 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19