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

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

Neuron 4725 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.8262. Min Act: -0.0000

Data Index: 695458 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 3.0900. Min Range: -3.0900

Max Act: 3.0900. Min Act: -0.0000

Data Index: 867940 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.6745. Min Act: -0.0000

Data Index: 399791 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.9180. Min Act: -0.0000

Data Index: 754700 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.6362. Min Act: -0.0000

Data Index: 1312940 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.5189. Min Act: -0.0000

Data Index: 681000 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.7079. Min Act: -0.0000

Data Index: 214765 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.5558. Min Act: -0.0000

Data Index: 563787 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.4009. Min Act: -0.0000

Data Index: 1014808 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.6325. Min Act: -0.0000

Data Index: 280611 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.5503. Min Act: -0.0000

Data Index: 1098624 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.3557. Min Act: -0.0000

Data Index: 333682 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.1598. Min Act: -0.0000

Data Index: 1183787 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.1739. Min Act: -0.0000

Data Index: 156823 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.1443. Min Act: -0.0000

Data Index: 1098529 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.1174. Min Act: -0.0000

Data Index: 22165 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.2225. Min Act: -0.0000

Data Index: 97468 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.2198. Min Act: -0.0000

Data Index: 1294730 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.2135. Min Act: -0.0000

Data Index: 899384 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 3.0900. Min Range: -3.0900

Max Act: 2.2154. Min Act: -0.0000

Data Index: 1033483 (C4 (Web Text))

Max Activating Token Index: 5