Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2251 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0246. Min Act: -0.0000

Data Index: 276610 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0232. Min Act: -0.0001

Data Index: 810967 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0227. Min Act: -0.0000

Data Index: 381568 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0225. Min Act: -0.0001

Data Index: 591348 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0227. Min Act: -0.0001

Data Index: 384120 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0206. Min Act: -0.0000

Data Index: 888048 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0213. Min Act: -0.0001

Data Index: 74790 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1312248 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0206. Min Act: -0.0000

Data Index: 1162696 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0219. Min Act: -0.0001

Data Index: 452918 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0205. Min Act: -0.0000

Data Index: 1468738 (Python Code)

Max Activating Token Index: 841

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0212. Min Act: -0.0001

Data Index: 481635 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0201. Min Act: -0.0001

Data Index: 109591 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0208. Min Act: -0.0000

Data Index: 415499 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0192. Min Act: -0.0001

Data Index: 290130 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0199. Min Act: -0.0000

Data Index: 412625 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0190. Min Act: -0.0000

Data Index: 1571706 (Python Code)

Max Activating Token Index: 655

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0194. Min Act: -0.0000

Data Index: 665865 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0188. Min Act: -0.0001

Data Index: 485806 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0200. Min Act: -0.0001

Data Index: 82326 (C4 (Web Text))

Max Activating Token Index: 805