Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4086 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3383. Min Act: -0.0001

Data Index: 1618553 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3003. Min Act: -0.0001

Data Index: 1582337 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3007. Min Act: -0.0001

Data Index: 1588393 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2474. Min Act: -0.0001

Data Index: 1464779 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2469. Min Act: -0.0001

Data Index: 1578573 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2425. Min Act: -0.0001

Data Index: 1364450 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2398. Min Act: -0.0002

Data Index: 1404716 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1561829 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2394. Min Act: -0.0001

Data Index: 1614381 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2377. Min Act: -0.0002

Data Index: 1462272 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2368. Min Act: -0.0002

Data Index: 1597406 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1585556 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2316. Min Act: -0.0001

Data Index: 1528115 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2297. Min Act: -0.0001

Data Index: 1477212 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1421697 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2320. Min Act: -0.0002

Data Index: 1476925 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1633809 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2238. Min Act: -0.0001

Data Index: 1556342 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1631051 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2231. Min Act: -0.0002

Data Index: 1602508 (Python Code)

Max Activating Token Index: 1023