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

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

Neuron 734 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: 0.0238. Min Range: -0.0238

Max Act: 0.0238. Min Act: -0.0002

Data Index: 214010 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1505979 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0194. Min Act: -0.0002

Data Index: 1610698 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0184. Min Act: -0.0002

Data Index: 620593 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1655156 (Python Code)

Max Activating Token Index: 28

Text #5

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1586971 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1603731 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1374488 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1398743 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1623155 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1395195 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1451720 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1639052 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1446643 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1533174 (Python Code)

Max Activating Token Index: 24

Text #15

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1579015 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1393457 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1616369 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0160. Min Act: -0.0002

Data Index: 1581745 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1623567 (Python Code)

Max Activating Token Index: 30