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

Dataset: The Pile

Neuron 1457 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0000

Data Index: 1001384 (The Pile)

Max Activating Token Index: 820

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0296. Min Act: -0.0000

Data Index: 1354942 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0285. Min Act: -0.0000

Data Index: 1515168 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1521479 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0270. Min Act: -0.0000

Data Index: 62688 (The Pile)

Max Activating Token Index: 751

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0289. Min Act: -0.0000

Data Index: 252571 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0277. Min Act: -0.0000

Data Index: 254489 (The Pile)

Max Activating Token Index: 311

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0269. Min Act: -0.0000

Data Index: 659142 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0265. Min Act: -0.0000

Data Index: 1920189 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0266. Min Act: -0.0000

Data Index: 924698 (The Pile)

Max Activating Token Index: 316

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0249. Min Act: -0.0000

Data Index: 1310866 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1819421 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0241. Min Act: 0.0000

Data Index: 1699365 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0249. Min Act: -0.0000

Data Index: 629091 (The Pile)

Max Activating Token Index: 697

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0253. Min Act: -0.0000

Data Index: 187298 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0236. Min Act: 0.0000

Data Index: 1696683 (The Pile)

Max Activating Token Index: 659

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0241. Min Act: -0.0000

Data Index: 1779318 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0241. Min Act: -0.0000

Data Index: 422566 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0241. Min Act: -0.0000

Data Index: 972036 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0229. Min Act: -0.0000

Data Index: 1196088 (The Pile)

Max Activating Token Index: 704