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

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

Neuron 2126 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2300. Min Act: -0.0002

Data Index: 387701 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2314. Min Act: -0.0002

Data Index: 945113 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2292. Min Act: -0.0003

Data Index: 55679 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2257. Min Act: -0.0002

Data Index: 268349 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2174. Min Act: -0.0002

Data Index: 344472 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2154. Min Act: -0.0002

Data Index: 885657 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2202. Min Act: -0.0002

Data Index: 610569 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2137. Min Act: -0.0002

Data Index: 181050 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2124. Min Act: -0.0002

Data Index: 1224182 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2080. Min Act: -0.0002

Data Index: 5314 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2074. Min Act: -0.0002

Data Index: 92085 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2041. Min Act: -0.0002

Data Index: 879204 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2041. Min Act: -0.0002

Data Index: 724841 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2114. Min Act: -0.0003

Data Index: 160006 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2074. Min Act: -0.0002

Data Index: 887048 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2000. Min Act: -0.0002

Data Index: 102260 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1991. Min Act: -0.0002

Data Index: 555775 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2010. Min Act: -0.0003

Data Index: 699952 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2000. Min Act: -0.0002

Data Index: 345261 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2042. Min Act: -0.0003

Data Index: 148516 (C4 (Web Text))

Max Activating Token Index: 21