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

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

Neuron 4641 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.8299. Min Act: 0.0000

Data Index: 549614 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.4783. Min Act: -0.0000

Data Index: 790916 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1857. Min Act: -0.0000

Data Index: 246923 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.2606. Min Act: -0.0000

Data Index: 154510 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.2339. Min Act: -0.0000

Data Index: 754819 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.2362. Min Act: -0.0000

Data Index: 750440 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1384. Min Act: -0.0000

Data Index: 581295 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.2075. Min Act: -0.0000

Data Index: 883890 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1351. Min Act: -0.0000

Data Index: 594192 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1332. Min Act: 0.0000

Data Index: 298235 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1867. Min Act: -0.0000

Data Index: 71681 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.0748. Min Act: -0.0000

Data Index: 670593 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1713. Min Act: -0.0000

Data Index: 786369 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1250. Min Act: 0.0000

Data Index: 1124961 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1313. Min Act: -0.0000

Data Index: 183955 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.0862. Min Act: 0.0000

Data Index: 654495 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.0665. Min Act: 0.0001

Data Index: 1243675 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1212. Min Act: 0.0000

Data Index: 1030414 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.8299. Min Range: -1.8299

Max Act: 1.1076. Min Act: -0.0000

Data Index: 968288 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 1.8299. Min Range: -1.8299

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1169191 (C4 (Web Text))

Max Activating Token Index: 551