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

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

Neuron 4045 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4434. Min Act: -0.0001

Data Index: 1214334 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4287. Min Act: -0.0001

Data Index: 106557 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4304. Min Act: -0.0001

Data Index: 71159 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3852. Min Act: -0.0001

Data Index: 1248786 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3779. Min Act: -0.0001

Data Index: 234340 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3509. Min Act: -0.0001

Data Index: 1074206 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3649. Min Act: -0.0001

Data Index: 308803 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3595. Min Act: -0.0001

Data Index: 1187580 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3341. Min Act: -0.0000

Data Index: 289807 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3443. Min Act: -0.0001

Data Index: 1241261 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3429. Min Act: -0.0001

Data Index: 1625346 (Python Code)

Max Activating Token Index: 906

Text #11

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3241. Min Act: -0.0001

Data Index: 1311237 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3420. Min Act: -0.0001

Data Index: 318309 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3414. Min Act: -0.0001

Data Index: 183575 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3192. Min Act: -0.0001

Data Index: 1553112 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3141. Min Act: -0.0001

Data Index: 91369 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3023. Min Act: -0.0001

Data Index: 402342 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3153. Min Act: -0.0001

Data Index: 1436375 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3345. Min Act: -0.0001

Data Index: 41821 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.2545. Min Act: -0.0001

Data Index: 1195701 (C4 (Web Text))

Max Activating Token Index: 682