Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 499 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0003

Data Index: 703484 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1615885 (Python Code)

Max Activating Token Index: 568

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1192188 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0265. Min Act: -0.0003

Data Index: 624407 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1216416 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1536130 (Python Code)

Max Activating Token Index: 177

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0263. Min Act: -0.0003

Data Index: 478449 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0257. Min Act: -0.0003

Data Index: 886604 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1398765 (Python Code)

Max Activating Token Index: 220

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0259. Min Act: -0.0003

Data Index: 843656 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0251. Min Act: -0.0003

Data Index: 625044 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0256. Min Act: -0.0003

Data Index: 565311 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0258. Min Act: -0.0003

Data Index: 818930 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1123287 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1110094 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0248. Min Act: -0.0003

Data Index: 530196 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0244. Min Act: -0.0003

Data Index: 410221 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1048438 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1172247 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0246. Min Act: -0.0003

Data Index: 995656 (C4 (Web Text))

Max Activating Token Index: 636