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

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

Neuron 1262 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1861. Min Act: -0.0001

Data Index: 640636 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1648. Min Act: -0.0001

Data Index: 844496 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1546. Min Act: -0.0001

Data Index: 694797 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1532. Min Act: -0.0001

Data Index: 492739 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1446. Min Act: -0.0002

Data Index: 718066 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1400. Min Act: -0.0002

Data Index: 1236103 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1520. Min Act: -0.0002

Data Index: 292323 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1475. Min Act: -0.0002

Data Index: 286034 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1454. Min Act: -0.0001

Data Index: 233544 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1461. Min Act: -0.0002

Data Index: 373147 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1395. Min Act: -0.0002

Data Index: 190367 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1396. Min Act: -0.0002

Data Index: 177605 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1409. Min Act: -0.0002

Data Index: 210362 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1292. Min Act: -0.0002

Data Index: 1056873 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1470. Min Act: -0.0002

Data Index: 257724 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1468. Min Act: -0.0002

Data Index: 981321 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1372. Min Act: -0.0001

Data Index: 555587 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1268. Min Act: -0.0001

Data Index: 224554 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1450. Min Act: -0.0002

Data Index: 1129344 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.1861. Min Range: -0.1861

Max Act: 0.1451. Min Act: -0.0002

Data Index: 1028169 (C4 (Web Text))

Max Activating Token Index: 393