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

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

Neuron 186 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0198. Min Act: -0.0005

Data Index: 242843 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0181. Min Act: -0.0005

Data Index: 460222 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0178. Min Act: -0.0005

Data Index: 1042121 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0174. Min Act: -0.0005

Data Index: 894204 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0180. Min Act: -0.0005

Data Index: 1238624 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0172. Min Act: -0.0005

Data Index: 1146137 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0172. Min Act: -0.0005

Data Index: 154743 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0168. Min Act: -0.0005

Data Index: 35859 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0167. Min Act: -0.0005

Data Index: 1079695 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0166. Min Act: -0.0005

Data Index: 459444 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0169. Min Act: -0.0005

Data Index: 641060 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0168. Min Act: -0.0006

Data Index: 368336 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0168. Min Act: -0.0005

Data Index: 616149 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0168. Min Act: -0.0005

Data Index: 1059937 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0164. Min Act: -0.0005

Data Index: 581228 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0167. Min Act: -0.0005

Data Index: 1025744 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1138588 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0166. Min Act: -0.0005

Data Index: 1212850 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0166. Min Act: -0.0005

Data Index: 194100 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.0198. Min Range: -0.0198

Max Act: 0.0166. Min Act: -0.0005

Data Index: 478099 (C4 (Web Text))

Max Activating Token Index: 577