Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3827 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2551. Min Act: -0.0000

Data Index: 301416 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2302. Min Act: -0.0000

Data Index: 142062 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2467. Min Act: -0.0000

Data Index: 272094 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1310630 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2393. Min Act: -0.0000

Data Index: 873587 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1099943 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2539. Min Act: -0.0000

Data Index: 52738 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2240. Min Act: -0.0000

Data Index: 928253 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2137. Min Act: -0.0000

Data Index: 76440 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1127191 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2105. Min Act: -0.0000

Data Index: 470744 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2183. Min Act: -0.0000

Data Index: 502900 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2074. Min Act: -0.0000

Data Index: 16048 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2050. Min Act: -0.0000

Data Index: 279248 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1336525 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2046. Min Act: -0.0000

Data Index: 850937 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2304. Min Act: -0.0000

Data Index: 700996 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1129209 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2058. Min Act: -0.0000

Data Index: 787576 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2034. Min Act: -0.0000

Data Index: 561694 (C4 (Web Text))

Max Activating Token Index: 689