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

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

Neuron 1024 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: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1528803 (Python Code)

Max Activating Token Index: 454

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1495299 (Python Code)

Max Activating Token Index: 679

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1570626 (Python Code)

Max Activating Token Index: 785

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1587009 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1510308 (Python Code)

Max Activating Token Index: 876

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1378231 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1494549 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1597000 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1407594 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1602507 (Python Code)

Max Activating Token Index: 504

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1371445 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1445125 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1442717 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1587999 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1543714 (Python Code)

Max Activating Token Index: 403

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1559619 (Python Code)

Max Activating Token Index: 988

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1527931 (Python Code)

Max Activating Token Index: 385

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1596770 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1399160 (Python Code)

Max Activating Token Index: 621

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1398259 (Python Code)

Max Activating Token Index: 476