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

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

Neuron 90 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.9787. Min Act: -0.0001

Data Index: 1619478 (Python Code)

Max Activating Token Index: 461

Text #1

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.9568. Min Act: -0.0001

Data Index: 1385275 (Python Code)

Max Activating Token Index: 402

Text #2

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.9232. Min Act: -0.0001

Data Index: 1608294 (Python Code)

Max Activating Token Index: 549

Text #3

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8206. Min Act: -0.0001

Data Index: 1480430 (Python Code)

Max Activating Token Index: 924

Text #4

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8727. Min Act: -0.0001

Data Index: 1395990 (Python Code)

Max Activating Token Index: 701

Text #5

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.9018. Min Act: -0.0001

Data Index: 1464812 (Python Code)

Max Activating Token Index: 505

Text #6

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8048. Min Act: -0.0001

Data Index: 1460059 (Python Code)

Max Activating Token Index: 551

Text #7

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8115. Min Act: -0.0001

Data Index: 1292206 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6330. Min Act: -0.0001

Data Index: 1472262 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7321. Min Act: -0.0001

Data Index: 1595574 (Python Code)

Max Activating Token Index: 624

Text #10

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7325. Min Act: -0.0001

Data Index: 1555212 (Python Code)

Max Activating Token Index: 406

Text #11

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7262. Min Act: -0.0001

Data Index: 1492886 (Python Code)

Max Activating Token Index: 379

Text #12

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6955. Min Act: -0.0001

Data Index: 1406270 (Python Code)

Max Activating Token Index: 479

Text #13

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6830. Min Act: -0.0001

Data Index: 878653 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6739. Min Act: -0.0001

Data Index: 1590622 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7854. Min Act: -0.0001

Data Index: 1645721 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6694. Min Act: -0.0001

Data Index: 1539604 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.5980. Min Act: -0.0001

Data Index: 844527 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6350. Min Act: -0.0001

Data Index: 1464038 (Python Code)

Max Activating Token Index: 325

Text #19

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6960. Min Act: -0.0001

Data Index: 1403912 (Python Code)

Max Activating Token Index: 118