Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3584 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0002

Data Index: 453365 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0248. Min Act: -0.0002

Data Index: 781585 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0228. Min Act: -0.0002

Data Index: 688110 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0231. Min Act: -0.0002

Data Index: 305668 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0219. Min Act: -0.0002

Data Index: 980606 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0232. Min Act: -0.0002

Data Index: 110706 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0219. Min Act: -0.0002

Data Index: 89958 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1169834 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0246. Min Act: -0.0002

Data Index: 270036 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0225. Min Act: -0.0002

Data Index: 490574 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0217. Min Act: -0.0002

Data Index: 922137 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1104340 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0209. Min Act: -0.0002

Data Index: 899782 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0213. Min Act: -0.0002

Data Index: 142047 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0208. Min Act: -0.0002

Data Index: 726531 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0207. Min Act: -0.0002

Data Index: 838273 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0210. Min Act: -0.0002

Data Index: 385945 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0204. Min Act: -0.0002

Data Index: 999628 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0204. Min Act: -0.0002

Data Index: 176626 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0213. Min Act: -0.0002

Data Index: 884375 (C4 (Web Text))

Max Activating Token Index: 166