Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 295 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0436. Min Act: -0.0006

Data Index: 267938 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0444. Min Act: -0.0006

Data Index: 608728 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0417. Min Act: -0.0006

Data Index: 612969 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0408. Min Act: -0.0005

Data Index: 62611 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0398. Min Act: -0.0006

Data Index: 577921 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0393. Min Act: -0.0005

Data Index: 435831 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0404. Min Act: -0.0006

Data Index: 744776 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0387. Min Act: -0.0006

Data Index: 384533 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0388. Min Act: -0.0006

Data Index: 465187 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0382. Min Act: -0.0005

Data Index: 586912 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0396. Min Act: -0.0005

Data Index: 204219 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0378. Min Act: -0.0006

Data Index: 720731 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0382. Min Act: -0.0006

Data Index: 1330257 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0376. Min Act: -0.0006

Data Index: 756329 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0364. Min Act: -0.0006

Data Index: 236512 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0378. Min Act: -0.0006

Data Index: 315645 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0362. Min Act: -0.0006

Data Index: 1140829 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1084426 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0360. Min Act: -0.0006

Data Index: 734222 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0367. Min Act: -0.0006

Data Index: 1151721 (C4 (Web Text))

Max Activating Token Index: 933