Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3945 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.4173. Min Act: -0.1700
Data Index: 2844032 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.4173. Min Act: -0.1700
Data Index: 8291501 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.2923. Min Act: -0.1700
Data Index: 5457360 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.1985. Min Act: -0.1700
Data Index: 2802533 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.2298. Min Act: -0.1698
Data Index: 5414685 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.1360. Min Act: -0.1697
Data Index: 4295748 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.1673. Min Act: -0.1700
Data Index: 2964995 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.1360. Min Act: -0.1700
Data Index: 5362162 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.1673. Min Act: -0.1700
Data Index: 5511981 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.1048. Min Act: -0.1700
Data Index: 5964500 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.1048. Min Act: -0.1700
Data Index: 774793 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.0735. Min Act: -0.1700
Data Index: 2469942 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.0735. Min Act: -0.1700
Data Index: 246950 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.0735. Min Act: -0.1700
Data Index: 3115877 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.0735. Min Act: -0.1700
Data Index: 3814722 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.1048. Min Act: -0.1700
Data Index: 4119694 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.0735. Min Act: -0.1700
Data Index: 6931213 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.0735. Min Act: -0.1700
Data Index: 3506959 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.0735. Min Act: -0.1700
Data Index: 7551929 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4173. Min Range: -5.4173
Max Act: 5.0423. Min Act: -0.1700
Data Index: 793487 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19