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

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

Neuron 3329 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1973. Min Act: -0.0001

Data Index: 216489 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1712. Min Act: -0.0001

Data Index: 897932 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1682. Min Act: -0.0001

Data Index: 97266 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1545. Min Act: -0.0001

Data Index: 642666 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1525. Min Act: -0.0001

Data Index: 884075 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1307. Min Act: -0.0001

Data Index: 134742 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1684. Min Act: -0.0001

Data Index: 234659 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1092580 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1437. Min Act: -0.0001

Data Index: 807403 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1454. Min Act: -0.0001

Data Index: 941556 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1409. Min Act: -0.0001

Data Index: 817884 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1436. Min Act: -0.0001

Data Index: 306942 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1294. Min Act: -0.0001

Data Index: 44569 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1367. Min Act: -0.0001

Data Index: 1104147 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1445. Min Act: -0.0001

Data Index: 885377 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1614508 (Python Code)

Max Activating Token Index: 844

Text #16

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1285. Min Act: -0.0001

Data Index: 90572 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1212. Min Act: -0.0001

Data Index: 604243 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1248. Min Act: -0.0001

Data Index: 680876 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.1973. Min Range: -0.1973

Max Act: 0.1295. Min Act: -0.0001

Data Index: 396080 (C4 (Web Text))

Max Activating Token Index: 178