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

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

Neuron 579 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: 0.1575. Min Range: -0.1575

Max Act: 0.1570. Min Act: -0.0001

Data Index: 488386 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1575. Min Act: -0.0001

Data Index: 999762 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1530. Min Act: -0.0001

Data Index: 973276 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1519. Min Act: -0.0001

Data Index: 521270 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1472. Min Act: -0.0001

Data Index: 410515 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1431. Min Act: -0.0001

Data Index: 588894 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1435. Min Act: -0.0001

Data Index: 886256 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1405. Min Act: -0.0001

Data Index: 342688 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1025005 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1423. Min Act: -0.0001

Data Index: 758879 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1091509 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1348192 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1393. Min Act: -0.0001

Data Index: 164496 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1385. Min Act: -0.0001

Data Index: 963437 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1379. Min Act: -0.0001

Data Index: 232214 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1384. Min Act: -0.0001

Data Index: 409155 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1328. Min Act: -0.0001

Data Index: 53452 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1347. Min Act: -0.0001

Data Index: 246102 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1316. Min Act: -0.0001

Data Index: 213722 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1339. Min Act: -0.0001

Data Index: 918779 (C4 (Web Text))

Max Activating Token Index: 464