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

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

Neuron 1168 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0221. Min Act: -0.0002

Data Index: 58877 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0214. Min Act: -0.0004

Data Index: 768826 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1359947 (Python Code)

Max Activating Token Index: 652

Text #3

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1444116 (Python Code)

Max Activating Token Index: 159

Text #4

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1025653 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0214. Min Act: -0.0003

Data Index: 180209 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1355789 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0206. Min Act: -0.0003

Data Index: 322620 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0207. Min Act: -0.0003

Data Index: 231070 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0207. Min Act: -0.0003

Data Index: 303647 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0199. Min Act: -0.0002

Data Index: 267168 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0190. Min Act: -0.0003

Data Index: 821933 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0198. Min Act: -0.0003

Data Index: 152090 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1324513 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0197. Min Act: -0.0003

Data Index: 365634 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1529616 (Python Code)

Max Activating Token Index: 989

Text #16

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1555907 (Python Code)

Max Activating Token Index: 359

Text #17

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1653122 (Python Code)

Max Activating Token Index: 577

Text #18

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0195. Min Act: -0.0003

Data Index: 18985 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0193. Min Act: -0.0003

Data Index: 892561 (C4 (Web Text))

Max Activating Token Index: 561