Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1478 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.2067. Min Act: -0.0003

Data Index: 128893 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.3710. Min Act: -0.0003

Data Index: 521446 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1958. Min Act: -0.0003

Data Index: 1051192 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1930. Min Act: -0.0003

Data Index: 202051 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1120. Min Act: -0.0003

Data Index: 347994 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1696. Min Act: -0.0003

Data Index: 368984 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.2396. Min Act: -0.0003

Data Index: 801184 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0860. Min Act: -0.0003

Data Index: 598692 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1409. Min Act: -0.0003

Data Index: 322221 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1351. Min Act: -0.0003

Data Index: 801112 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1257. Min Act: -0.0003

Data Index: 446040 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1228. Min Act: -0.0003

Data Index: 691278 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1577. Min Act: -0.0003

Data Index: 459161 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0784. Min Act: -0.0003

Data Index: 1006197 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.2024. Min Act: -0.0003

Data Index: 715163 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0324. Min Act: -0.0003

Data Index: 348980 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0514. Min Act: -0.0003

Data Index: 686089 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.0476. Min Act: -0.0003

Data Index: 714183 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1005. Min Act: -0.0003

Data Index: 972772 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 1.3710. Min Range: -1.3710

Max Act: 1.1036. Min Act: -0.0003

Data Index: 328358 (C4 (Web Text))

Max Activating Token Index: 46