Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2701 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.4353. Min Act: -0.1700
Data Index: 1236778 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.4353. Min Act: -0.1700
Data Index: 7857167 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.3728. Min Act: -0.1700
Data Index: 7299711 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.2791. Min Act: -0.1700
Data Index: 7992585 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.2478. Min Act: -0.1700
Data Index: 5852268 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.1853. Min Act: -0.1700
Data Index: 6678289 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.1541. Min Act: -0.1700
Data Index: 8010712 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.1228. Min Act: -0.1700
Data Index: 811917 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.0916. Min Act: -0.1700
Data Index: 843620 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.0916. Min Act: -0.1700
Data Index: 370794 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.0916. Min Act: -0.1700
Data Index: 7882388 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.0603. Min Act: -0.1700
Data Index: 5923299 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.0603. Min Act: -0.1700
Data Index: 3363971 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.0291. Min Act: -0.1700
Data Index: 5519023 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.0291. Min Act: -0.1700
Data Index: 2198263 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.0291. Min Act: -0.1700
Data Index: 7673673 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4353. Min Range: -6.4353
Max Act: 6.0291. Min Act: -0.1700
Data Index: 4221525 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4353. Min Range: -6.4353
Max Act: 5.9978. Min Act: -0.1700
Data Index: 3871932 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4353. Min Range: -6.4353
Max Act: 5.9978. Min Act: -0.1700
Data Index: 2282147 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4353. Min Range: -6.4353
Max Act: 5.9666. Min Act: -0.1700
Data Index: 4881393 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19