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

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

Neuron 221 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: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0003

Data Index: 895837 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0003

Data Index: 785043 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0459. Min Act: -0.0003

Data Index: 236774 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1002443 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0364. Min Act: -0.0003

Data Index: 640560 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0413. Min Act: -0.0003

Data Index: 445012 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1135194 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0381. Min Act: -0.0003

Data Index: 893368 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1237673 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0414. Min Act: -0.0003

Data Index: 144411 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0377. Min Act: -0.0003

Data Index: 887442 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0411. Min Act: -0.0003

Data Index: 36721 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0403. Min Act: -0.0003

Data Index: 526439 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0349. Min Act: -0.0003

Data Index: 824683 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0361. Min Act: -0.0003

Data Index: 425548 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0352. Min Act: -0.0003

Data Index: 939918 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1261958 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0384. Min Act: -0.0003

Data Index: 981337 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0369. Min Act: -0.0003

Data Index: 790972 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1059691 (C4 (Web Text))

Max Activating Token Index: 393