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

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

Neuron 2033 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0000

Data Index: 939290 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0497. Min Act: -0.0000

Data Index: 904168 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0446. Min Act: -0.0000

Data Index: 494057 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0408. Min Act: -0.0000

Data Index: 336282 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0421. Min Act: -0.0000

Data Index: 56538 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0398. Min Act: -0.0000

Data Index: 293510 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0414. Min Act: -0.0000

Data Index: 318369 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0395. Min Act: -0.0000

Data Index: 1048020 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1652633 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0376. Min Act: -0.0000

Data Index: 256975 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0415. Min Act: -0.0000

Data Index: 246298 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0361. Min Act: -0.0000

Data Index: 305718 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0353. Min Act: -0.0000

Data Index: 374783 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0358. Min Act: -0.0000

Data Index: 1408418 (Python Code)

Max Activating Token Index: 438

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0357. Min Act: -0.0000

Data Index: 894220 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1591682 (Python Code)

Max Activating Token Index: 562

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1509150 (Python Code)

Max Activating Token Index: 719

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1242653 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1436537 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0357. Min Act: -0.0000

Data Index: 1408263 (Python Code)

Max Activating Token Index: 537