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

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

Neuron 1959 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1602205 (Python Code)

Max Activating Token Index: 760

Text #1

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1645376 (Python Code)

Max Activating Token Index: 698

Text #2

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2729. Min Act: -0.0001

Data Index: 127973 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2594. Min Act: -0.0000

Data Index: 1643644 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1437484 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1568259 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1525382 (Python Code)

Max Activating Token Index: 415

Text #7

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1528697 (Python Code)

Max Activating Token Index: 619

Text #8

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1569120 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1543564 (Python Code)

Max Activating Token Index: 185

Text #10

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1447370 (Python Code)

Max Activating Token Index: 275

Text #11

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1534521 (Python Code)

Max Activating Token Index: 971

Text #12

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2302. Min Act: -0.0001

Data Index: 1521664 (Python Code)

Max Activating Token Index: 379

Text #13

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1390149 (Python Code)

Max Activating Token Index: 365

Text #14

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1635199 (Python Code)

Max Activating Token Index: 602

Text #15

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1555983 (Python Code)

Max Activating Token Index: 381

Text #16

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2140. Min Act: -0.0001

Data Index: 1472441 (Python Code)

Max Activating Token Index: 732

Text #17

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2232. Min Act: -0.0001

Data Index: 1376268 (Python Code)

Max Activating Token Index: 813

Text #18

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1475209 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1588536 (Python Code)

Max Activating Token Index: 520