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

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

Neuron 1848 in Layer 0

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: 0.0255. Min Range: -0.0255

Max Act: 0.0255. Min Act: -0.0001

Data Index: 147056 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0235. Min Act: -0.0001

Data Index: 637694 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0221. Min Act: -0.0001

Data Index: 528463 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0219. Min Act: -0.0001

Data Index: 186474 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1448425 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0202. Min Act: -0.0001

Data Index: 211196 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0204. Min Act: -0.0001

Data Index: 854454 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0200. Min Act: -0.0001

Data Index: 913957 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1060641 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0197. Min Act: -0.0001

Data Index: 955715 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0197. Min Act: -0.0001

Data Index: 694126 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1604198 (Python Code)

Max Activating Token Index: 356

Text #12

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0189. Min Act: -0.0001

Data Index: 734629 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0191. Min Act: -0.0001

Data Index: 140763 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1344762 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0186. Min Act: -0.0001

Data Index: 399521 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1219965 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0184. Min Act: -0.0001

Data Index: 1135679 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0184. Min Act: -0.0001

Data Index: 937980 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0255. Min Range: -0.0255

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1438425 (Python Code)

Max Activating Token Index: 612