Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 452 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0006

Data Index: 314822 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1411172 (Python Code)

Max Activating Token Index: 234

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1382770 (Python Code)

Max Activating Token Index: 959

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1509807 (Python Code)

Max Activating Token Index: 762

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0217. Min Act: -0.0006

Data Index: 544127 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1628764 (Python Code)

Max Activating Token Index: 730

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1422031 (Python Code)

Max Activating Token Index: 239

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0186. Min Act: -0.0006

Data Index: 837331 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0197. Min Act: -0.0006

Data Index: 493105 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1440815 (Python Code)

Max Activating Token Index: 461

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1501587 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1491192 (Python Code)

Max Activating Token Index: 561

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1639216 (Python Code)

Max Activating Token Index: 441

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1655744 (Python Code)

Max Activating Token Index: 43

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1405067 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1647697 (Python Code)

Max Activating Token Index: 73

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1636736 (Python Code)

Max Activating Token Index: 517

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1624306 (Python Code)

Max Activating Token Index: 886

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1554149 (Python Code)

Max Activating Token Index: 59

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0149. Min Act: -0.0006

Data Index: 357840 (C4 (Web Text))

Max Activating Token Index: 136