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

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

Neuron 2982 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: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1281412 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0362. Min Act: -0.0003

Data Index: 454143 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0361. Min Act: -0.0003

Data Index: 373472 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0359. Min Act: -0.0003

Data Index: 770819 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0354. Min Act: -0.0003

Data Index: 917201 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1524199 (Python Code)

Max Activating Token Index: 710

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0345. Min Act: -0.0003

Data Index: 206647 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0365. Min Act: -0.0003

Data Index: 452207 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0353. Min Act: -0.0003

Data Index: 544683 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1275352 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0292. Min Act: -0.0003

Data Index: 28798 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0339. Min Act: -0.0003

Data Index: 878853 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0340. Min Act: -0.0003

Data Index: 520634 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0340. Min Act: -0.0003

Data Index: 418457 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0326. Min Act: -0.0003

Data Index: 232567 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0318. Min Act: -0.0003

Data Index: 653891 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1134741 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1068637 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1269237 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1309807 (C4 (Web Text))

Max Activating Token Index: 526