Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5395 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0590. Min Act: -0.0002

Data Index: 647374 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0002

Data Index: 983034 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0481. Min Act: -0.0002

Data Index: 298843 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0472. Min Act: -0.0002

Data Index: 615200 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0461. Min Act: -0.0002

Data Index: 68324 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1296289 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0444. Min Act: -0.0002

Data Index: 174265 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0388. Min Act: -0.0002

Data Index: 453173 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0390. Min Act: -0.0002

Data Index: 517829 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1276485 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0380. Min Act: -0.0002

Data Index: 271937 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0372. Min Act: -0.0002

Data Index: 282020 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0367. Min Act: -0.0002

Data Index: 428470 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0351. Min Act: -0.0002

Data Index: 176456 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0348. Min Act: -0.0002

Data Index: 654752 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0358. Min Act: -0.0002

Data Index: 578077 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0348. Min Act: -0.0002

Data Index: 528385 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0346. Min Act: -0.0002

Data Index: 456314 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0347. Min Act: -0.0002

Data Index: 377637 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0356. Min Act: -0.0002

Data Index: 934464 (C4 (Web Text))

Max Activating Token Index: 560