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

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

Neuron 2173 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0465. Min Act: -0.0001

Data Index: 409554 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1127046 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0335. Min Act: -0.0001

Data Index: 780688 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0310. Min Act: -0.0001

Data Index: 61663 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0320. Min Act: -0.0001

Data Index: 304747 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0311. Min Act: -0.0001

Data Index: 684351 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0291. Min Act: -0.0001

Data Index: 535078 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0273. Min Act: -0.0001

Data Index: 411052 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0282. Min Act: -0.0001

Data Index: 89216 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0258. Min Act: -0.0001

Data Index: 770888 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0279. Min Act: -0.0001

Data Index: 211180 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0281. Min Act: -0.0001

Data Index: 246957 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1288168 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0281. Min Act: -0.0001

Data Index: 790088 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0245. Min Act: -0.0001

Data Index: 352084 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0246. Min Act: -0.0001

Data Index: 861555 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0277. Min Act: -0.0001

Data Index: 506897 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1302220 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0270. Min Act: -0.0001

Data Index: 899959 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0260. Min Act: -0.0001

Data Index: 616871 (C4 (Web Text))

Max Activating Token Index: 769