Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 427 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1568919 (Python Code)

Max Activating Token Index: 93

Text #1

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0428. Min Act: -0.0003

Data Index: 307501 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1525563 (Python Code)

Max Activating Token Index: 661

Text #3

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1269304 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1255335 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0390. Min Act: 0.0002

Data Index: 1373001 (Python Code)

Max Activating Token Index: 411

Text #6

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1265015 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1194809 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0373. Min Act: -0.0003

Data Index: 215214 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0369. Min Act: -0.0003

Data Index: 587382 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0360. Min Act: -0.0004

Data Index: 227222 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1010958 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0363. Min Act: 0.0001

Data Index: 366208 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0364. Min Act: 0.0001

Data Index: 514049 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0371. Min Act: -0.0002

Data Index: 221873 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0371. Min Act: -0.0003

Data Index: 634950 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1287752 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1634960 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0360. Min Act: -0.0003

Data Index: 326872 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0350. Min Act: -0.0004

Data Index: 724340 (C4 (Web Text))

Max Activating Token Index: 814