Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7236. Min Range: -6.7236
Max Act: 6.7236. Min Act: -0.1700
Data Index: 8771965 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7236. Min Range: -6.7236
Max Act: 6.6298. Min Act: -0.1700
Data Index: 4965456 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7236. Min Range: -6.7236
Max Act: 6.2861. Min Act: -0.1700
Data Index: 8077773 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7236. Min Range: -6.7236
Max Act: 6.1611. Min Act: -0.1700
Data Index: 587457 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7236. Min Range: -6.7236
Max Act: 6.1298. Min Act: -0.1700
Data Index: 5531557 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7236. Min Range: -6.7236
Max Act: 6.0986. Min Act: -0.1700
Data Index: 5565307 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7236. Min Range: -6.7236
Max Act: 6.0673. Min Act: -0.1700
Data Index: 5472434 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7236. Min Range: -6.7236
Max Act: 6.0361. Min Act: -0.1700
Data Index: 2091760 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7236. Min Range: -6.7236
Max Act: 6.0361. Min Act: -0.1700
Data Index: 1397734 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.9736. Min Act: -0.1700
Data Index: 1395826 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.9423. Min Act: -0.1700
Data Index: 954656 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.8798. Min Act: -0.1700
Data Index: 7279978 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.8486. Min Act: -0.1700
Data Index: 6519994 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.8173. Min Act: -0.1700
Data Index: 2583616 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.8173. Min Act: -0.1700
Data Index: 2158830 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.8486. Min Act: -0.1700
Data Index: 1763763 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.8173. Min Act: -0.1700
Data Index: 3226160 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.8173. Min Act: -0.1700
Data Index: 6078693 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.7861. Min Act: -0.1700
Data Index: 8150067 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7236. Min Range: -6.7236
Max Act: 5.7861. Min Act: -0.1700
Data Index: 3003325 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19