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

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

Neuron 4195 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.4700. Min Act: -0.0001

Data Index: 633585 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.3110. Min Act: -0.0001

Data Index: 306051 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.3199. Min Act: -0.0001

Data Index: 138189 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2080. Min Act: -0.0001

Data Index: 335015 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2209. Min Act: -0.0001

Data Index: 857532 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.3238. Min Act: -0.0001

Data Index: 1086992 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2136. Min Act: -0.0001

Data Index: 75924 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1933. Min Act: -0.0001

Data Index: 264949 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1386. Min Act: -0.0001

Data Index: 1159600 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2029. Min Act: -0.0001

Data Index: 308947 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2104. Min Act: -0.0001

Data Index: 699698 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2289. Min Act: -0.0001

Data Index: 896008 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2029. Min Act: -0.0001

Data Index: 1075660 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.0792. Min Act: -0.0001

Data Index: 434040 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2194. Min Act: -0.0001

Data Index: 270559 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.1132. Min Act: -0.0001

Data Index: 483243 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2007. Min Act: -0.0001

Data Index: 336686 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2260. Min Act: -0.0001

Data Index: 1044567 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2159. Min Act: -0.0001

Data Index: 451813 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 1.4700. Min Range: -1.4700

Max Act: 1.2905. Min Act: -0.0001

Data Index: 1138857 (C4 (Web Text))

Max Activating Token Index: 216