Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 306 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1506576 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1641300 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1626859 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1495389 (Python Code)

Max Activating Token Index: 299

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1645232 (Python Code)

Max Activating Token Index: 271

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1531406 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1448919 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1491553 (Python Code)

Max Activating Token Index: 135

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1472680 (Python Code)

Max Activating Token Index: 400

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1405387 (Python Code)

Max Activating Token Index: 1004

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1551330 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1542193 (Python Code)

Max Activating Token Index: 953

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1399524 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1423742 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1502233 (Python Code)

Max Activating Token Index: 449

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1538974 (Python Code)

Max Activating Token Index: 545

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1497759 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1544980 (Python Code)

Max Activating Token Index: 976

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1640984 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1649691 (Python Code)

Max Activating Token Index: 951