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

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

Neuron 1618 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0001

Data Index: 947274 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0279. Min Act: -0.0001

Data Index: 673370 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0243. Min Act: -0.0001

Data Index: 965246 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1198249 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1650160 (Python Code)

Max Activating Token Index: 942

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0212. Min Act: -0.0001

Data Index: 189907 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1509893 (Python Code)

Max Activating Token Index: 814

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1372080 (Python Code)

Max Activating Token Index: 745

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0194. Min Act: -0.0001

Data Index: 799237 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1353837 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0209. Min Act: -0.0001

Data Index: 335628 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1475620 (Python Code)

Max Activating Token Index: 985

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0197. Min Act: -0.0001

Data Index: 172709 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0188. Min Act: -0.0001

Data Index: 646010 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1638594 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0186. Min Act: -0.0001

Data Index: 938917 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1645929 (Python Code)

Max Activating Token Index: 756

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1370 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0184. Min Act: -0.0001

Data Index: 685462 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0191. Min Act: -0.0001

Data Index: 408802 (C4 (Web Text))

Max Activating Token Index: 923