Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4419 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1609. Min Range: -5.1609
Max Act: 5.1297. Min Act: -0.1700
Data Index: 1972815 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1609. Min Range: -5.1609
Max Act: 5.1609. Min Act: -0.1700
Data Index: 4879839 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1609. Min Range: -5.1609
Max Act: 5.0359. Min Act: -0.1700
Data Index: 7905241 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1609. Min Range: -5.1609
Max Act: 5.0359. Min Act: -0.1700
Data Index: 2398208 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1609. Min Range: -5.1609
Max Act: 5.0047. Min Act: -0.1700
Data Index: 308646 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1609. Min Range: -5.1609
Max Act: 5.0047. Min Act: -0.1700
Data Index: 6680199 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1609. Min Range: -5.1609
Max Act: 5.0047. Min Act: -0.1700
Data Index: 6624853 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1609. Min Range: -5.1609
Max Act: 5.0047. Min Act: -0.1700
Data Index: 1866325 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.9734. Min Act: -0.1700
Data Index: 1425204 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1609. Min Range: -5.1609
Max Act: 5.0047. Min Act: -0.1700
Data Index: 7327847 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.9422. Min Act: -0.1700
Data Index: 119213 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.9422. Min Act: -0.1700
Data Index: 5774001 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.9109. Min Act: -0.1700
Data Index: 47460 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.9109. Min Act: -0.1700
Data Index: 2789051 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.9109. Min Act: -0.1700
Data Index: 5594587 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.9109. Min Act: -0.1700
Data Index: 5777207 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.9109. Min Act: -0.1700
Data Index: 2652060 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.8484. Min Act: -0.1700
Data Index: 4829778 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.8797. Min Act: -0.1700
Data Index: 7297108 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1609. Min Range: -5.1609
Max Act: 4.8797. Min Act: -0.1700
Data Index: 2647013 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19