Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3469 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0357. Min Act: -0.0004

Data Index: 579396 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1081766 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0403. Min Act: -0.0003

Data Index: 17060 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0387. Min Act: -0.0003

Data Index: 376215 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1309033 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0369. Min Act: -0.0003

Data Index: 937073 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0432. Min Act: -0.0003

Data Index: 801464 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0361. Min Act: -0.0003

Data Index: 887804 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0409. Min Act: -0.0003

Data Index: 437351 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0358. Min Act: -0.0003

Data Index: 189240 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0362. Min Act: -0.0003

Data Index: 678574 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1201967 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0362. Min Act: -0.0003

Data Index: 168745 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0362. Min Act: -0.0003

Data Index: 191696 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0353. Min Act: -0.0003

Data Index: 150776 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0354. Min Act: -0.0003

Data Index: 3004 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0342. Min Act: -0.0003

Data Index: 111431 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1240605 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0354. Min Act: -0.0003

Data Index: 429646 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0354. Min Act: -0.0003

Data Index: 795245 (C4 (Web Text))

Max Activating Token Index: 178