Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4898 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1482365 (Python Code)

Max Activating Token Index: 759

Text #1

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1586150 (Python Code)

Max Activating Token Index: 850

Text #2

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1451391 (Python Code)

Max Activating Token Index: 872

Text #3

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1565037 (Python Code)

Max Activating Token Index: 892

Text #4

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1214. Min Act: -0.0000

Data Index: 112854 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1595658 (Python Code)

Max Activating Token Index: 974

Text #6

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1334150 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1435698 (Python Code)

Max Activating Token Index: 304

Text #8

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1464006 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1538881 (Python Code)

Max Activating Token Index: 1017

Text #10

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1019. Min Act: -0.0000

Data Index: 453714 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1594912 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1372932 (Python Code)

Max Activating Token Index: 990

Text #13

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1527424 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1460667 (Python Code)

Max Activating Token Index: 962

Text #15

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1045694 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0872. Min Act: -0.0000

Data Index: 556216 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1389792 (Python Code)

Max Activating Token Index: 998

Text #18

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0871. Min Act: -0.0000

Data Index: 375619 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1500322 (Python Code)

Max Activating Token Index: 928