Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4772 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1008. Min Range: -5.1008
Max Act: 5.1008. Min Act: -0.1700
Data Index: 5386684 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1008. Min Range: -5.1008
Max Act: 5.0695. Min Act: -0.1700
Data Index: 3256223 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.7883. Min Act: -0.1700
Data Index: 8628984 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.7570. Min Act: -0.1700
Data Index: 284943 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.7570. Min Act: -0.1700
Data Index: 163797 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.6945. Min Act: -0.1700
Data Index: 1576 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.6945. Min Act: -0.1700
Data Index: 8222777 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.6945. Min Act: -0.1700
Data Index: 2003540 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.6633. Min Act: -0.1700
Data Index: 192309 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.6945. Min Act: -0.1700
Data Index: 4562127 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.6320. Min Act: -0.1700
Data Index: 1682645 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.6320. Min Act: -0.1700
Data Index: 7478062 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.6008. Min Act: -0.1700
Data Index: 1572324 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.6008. Min Act: -0.1700
Data Index: 3305054 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.6320. Min Act: -0.1700
Data Index: 7823931 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.5695. Min Act: -0.1700
Data Index: 1754826 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.5383. Min Act: -0.1700
Data Index: 6527494 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.5383. Min Act: -0.1700
Data Index: 7956503 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.5070. Min Act: -0.1700
Data Index: 6644237 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1008. Min Range: -5.1008
Max Act: 4.5070. Min Act: -0.1700
Data Index: 2930127 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19