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

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

Neuron 2455 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: 0.0904. Min Range: -0.0904

Max Act: 0.0904. Min Act: -0.0002

Data Index: 51850 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0475. Min Act: -0.0002

Data Index: 700526 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0398. Min Act: -0.0001

Data Index: 493055 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0363. Min Act: -0.0001

Data Index: 421485 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0411. Min Act: -0.0001

Data Index: 679194 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0323. Min Act: -0.0001

Data Index: 263900 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0307. Min Act: -0.0002

Data Index: 205095 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1112936 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0384. Min Act: -0.0002

Data Index: 485564 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1629081 (Python Code)

Max Activating Token Index: 54

Text #10

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1529418 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0294. Min Act: -0.0001

Data Index: 588019 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0312. Min Act: -0.0001

Data Index: 580910 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0329. Min Act: -0.0002

Data Index: 541665 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0328. Min Act: -0.0001

Data Index: 119526 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1025936 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0336. Min Act: -0.0002

Data Index: 951589 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1034286 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0299. Min Act: -0.0001

Data Index: 232835 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1368796 (Python Code)

Max Activating Token Index: 368