Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4840 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3804. Min Range: -8.3804
Max Act: 8.3804. Min Act: -0.1700
Data Index: 176542 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3804. Min Range: -8.3804
Max Act: 8.3179. Min Act: -0.1700
Data Index: 8334065 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3804. Min Range: -8.3804
Max Act: 8.2554. Min Act: -0.1700
Data Index: 3680953 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3804. Min Range: -8.3804
Max Act: 8.1929. Min Act: -0.1700
Data Index: 2499667 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3804. Min Range: -8.3804
Max Act: 8.1929. Min Act: -0.1700
Data Index: 7461691 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3804. Min Range: -8.3804
Max Act: 8.0679. Min Act: -0.1700
Data Index: 8802577 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3804. Min Range: -8.3804
Max Act: 8.0054. Min Act: -0.1700
Data Index: 1918167 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3804. Min Range: -8.3804
Max Act: 8.0054. Min Act: -0.1700
Data Index: 4391602 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3804. Min Range: -8.3804
Max Act: 8.0054. Min Act: -0.1700
Data Index: 6366266 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3804. Min Range: -8.3804
Max Act: 8.0679. Min Act: -0.1700
Data Index: 78760 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3804. Min Range: -8.3804
Max Act: 7.9429. Min Act: -0.1700
Data Index: 2170362 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3804. Min Range: -8.3804
Max Act: 7.8804. Min Act: -0.1700
Data Index: 6867833 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3804. Min Range: -8.3804
Max Act: 7.8804. Min Act: -0.1700
Data Index: 3223214 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3804. Min Range: -8.3804
Max Act: 7.8179. Min Act: -0.1700
Data Index: 3684048 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3804. Min Range: -8.3804
Max Act: 7.8179. Min Act: -0.1700
Data Index: 82623 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3804. Min Range: -8.3804
Max Act: 7.8179. Min Act: -0.1700
Data Index: 4300805 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3804. Min Range: -8.3804
Max Act: 7.8179. Min Act: -0.1700
Data Index: 276174 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3804. Min Range: -8.3804
Max Act: 7.8179. Min Act: -0.1700
Data Index: 1985449 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3804. Min Range: -8.3804
Max Act: 7.7554. Min Act: -0.1700
Data Index: 6782139 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3804. Min Range: -8.3804
Max Act: 7.7554. Min Act: -0.1700
Data Index: 4025968 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19