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

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

Neuron 3496 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: 0.0304. Min Range: -0.0304

Max Act: 0.0304. Min Act: -0.0002

Data Index: 111938 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0252. Min Act: -0.0002

Data Index: 433087 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0253. Min Act: -0.0002

Data Index: 136363 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0229. Min Act: -0.0002

Data Index: 114101 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1166534 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1503063 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0218. Min Act: -0.0002

Data Index: 515189 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1417607 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1472388 (Python Code)

Max Activating Token Index: 1015

Text #9

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1473908 (Python Code)

Max Activating Token Index: 668

Text #10

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1396583 (Python Code)

Max Activating Token Index: 534

Text #11

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1364231 (Python Code)

Max Activating Token Index: 644

Text #12

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1534323 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1151435 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1555379 (Python Code)

Max Activating Token Index: 597

Text #15

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1508854 (Python Code)

Max Activating Token Index: 759

Text #16

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1534495 (Python Code)

Max Activating Token Index: 692

Text #17

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1543543 (Python Code)

Max Activating Token Index: 837

Text #18

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1544308 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 0.0304. Min Range: -0.0304

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1597755 (Python Code)

Max Activating Token Index: 318