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

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

Neuron 3138 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1054399 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0590. Min Act: -0.0001

Data Index: 70041 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0517. Min Act: -0.0001

Data Index: 101260 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0483. Min Act: -0.0001

Data Index: 973541 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0302. Min Act: -0.0001

Data Index: 990869 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0460. Min Act: -0.0001

Data Index: 803091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0451. Min Act: -0.0001

Data Index: 224509 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0461. Min Act: -0.0001

Data Index: 807631 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1547429 (Python Code)

Max Activating Token Index: 440

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0438. Min Act: -0.0001

Data Index: 97833 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0504. Min Act: -0.0001

Data Index: 797521 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0434. Min Act: -0.0001

Data Index: 244513 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0430. Min Act: -0.0001

Data Index: 549107 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0406. Min Act: -0.0001

Data Index: 221069 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0370. Min Act: -0.0001

Data Index: 450906 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0366. Min Act: -0.0001

Data Index: 457383 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0381. Min Act: -0.0001

Data Index: 295472 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1300678 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0300. Min Act: -0.0001

Data Index: 473711 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0344. Min Act: -0.0001

Data Index: 608074 (C4 (Web Text))

Max Activating Token Index: 489