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

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

Neuron 585 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0341. Min Act: -0.0003

Data Index: 192285 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0279. Min Act: -0.0003

Data Index: 446725 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1073318 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0266. Min Act: -0.0003

Data Index: 514076 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0246. Min Act: -0.0003

Data Index: 615663 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0245. Min Act: -0.0003

Data Index: 994962 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1140053 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1108804 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0250. Min Act: -0.0003

Data Index: 807977 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0239. Min Act: -0.0002

Data Index: 929932 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0242. Min Act: -0.0003

Data Index: 92216 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0237. Min Act: -0.0003

Data Index: 833229 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0233. Min Act: -0.0002

Data Index: 792944 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0232. Min Act: -0.0003

Data Index: 328888 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0224. Min Act: -0.0003

Data Index: 942900 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0233. Min Act: -0.0002

Data Index: 426163 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0234. Min Act: -0.0003

Data Index: 798040 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0228. Min Act: -0.0003

Data Index: 990131 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0228. Min Act: -0.0002

Data Index: 173890 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0232. Min Act: -0.0003

Data Index: 801611 (C4 (Web Text))

Max Activating Token Index: 601