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

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

Neuron 433 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: 0.0417. Min Range: -0.0417

Max Act: 0.0404. Min Act: -0.0006

Data Index: 1235683 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0006

Data Index: 1073070 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0408. Min Act: -0.0006

Data Index: 818308 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0384. Min Act: -0.0006

Data Index: 1334814 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0377. Min Act: -0.0006

Data Index: 189720 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0390. Min Act: -0.0006

Data Index: 796740 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0373. Min Act: -0.0006

Data Index: 527110 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0376. Min Act: -0.0006

Data Index: 455632 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0369. Min Act: -0.0006

Data Index: 926144 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0381. Min Act: -0.0006

Data Index: 1179753 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0374. Min Act: -0.0006

Data Index: 1075081 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0369. Min Act: -0.0006

Data Index: 1350972 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0366. Min Act: -0.0006

Data Index: 1210925 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0366. Min Act: -0.0006

Data Index: 726592 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0358. Min Act: -0.0006

Data Index: 359533 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0369. Min Act: -0.0006

Data Index: 127122 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1157411 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0326. Min Act: -0.0006

Data Index: 1346260 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0362. Min Act: -0.0006

Data Index: 52937 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0344. Min Act: -0.0006

Data Index: 563443 (C4 (Web Text))

Max Activating Token Index: 742