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

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

Neuron 2198 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: 0.1831. Min Range: -0.1831

Max Act: 0.1831. Min Act: -0.0002

Data Index: 348417 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1665. Min Act: -0.0002

Data Index: 565298 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1347465 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1134622 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1586. Min Act: -0.0002

Data Index: 1218471 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1447. Min Act: -0.0002

Data Index: 95692 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1537. Min Act: -0.0002

Data Index: 167991 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1383. Min Act: -0.0002

Data Index: 236555 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1332. Min Act: -0.0002

Data Index: 172328 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1280. Min Act: -0.0002

Data Index: 564518 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1419. Min Act: -0.0002

Data Index: 773972 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1146. Min Act: -0.0001

Data Index: 831763 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1218. Min Act: -0.0001

Data Index: 757594 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1298. Min Act: -0.0002

Data Index: 530523 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.0992. Min Act: -0.0001

Data Index: 810243 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1280. Min Act: -0.0002

Data Index: 332570 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1232. Min Act: -0.0002

Data Index: 248208 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1307. Min Act: -0.0002

Data Index: 1063745 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1296. Min Act: -0.0002

Data Index: 381781 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1251. Min Act: -0.0002

Data Index: 824103 (C4 (Web Text))

Max Activating Token Index: 599