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

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

Neuron 980 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: 2.2480. Min Range: -2.2480

Max Act: 2.2480. Min Act: -0.0001

Data Index: 1404445 (Python Code)

Max Activating Token Index: 407

Text #1

Max Range: 2.2480. Min Range: -2.2480

Max Act: 2.1825. Min Act: -0.0000

Data Index: 1593996 (Python Code)

Max Activating Token Index: 253

Text #2

Max Range: 2.2480. Min Range: -2.2480

Max Act: 2.1519. Min Act: -0.0001

Data Index: 1544405 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 2.2480. Min Range: -2.2480

Max Act: 2.0127. Min Act: -0.0000

Data Index: 1508000 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 2.2480. Min Range: -2.2480

Max Act: 2.1123. Min Act: -0.0001

Data Index: 1621171 (Python Code)

Max Activating Token Index: 53

Text #5

Max Range: 2.2480. Min Range: -2.2480

Max Act: 2.0528. Min Act: -0.0001

Data Index: 1438867 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 2.2480. Min Range: -2.2480

Max Act: 2.0067. Min Act: -0.0000

Data Index: 1412060 (Python Code)

Max Activating Token Index: 675

Text #7

Max Range: 2.2480. Min Range: -2.2480

Max Act: 2.0518. Min Act: -0.0000

Data Index: 1379557 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 2.2480. Min Range: -2.2480

Max Act: 2.0352. Min Act: -0.0001

Data Index: 1448077 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 2.2480. Min Range: -2.2480

Max Act: 2.1279. Min Act: -0.0001

Data Index: 1537550 (Python Code)

Max Activating Token Index: 551

Text #10

Max Range: 2.2480. Min Range: -2.2480

Max Act: 1.8913. Min Act: -0.0001

Data Index: 1383618 (Python Code)

Max Activating Token Index: 250

Text #11

Max Range: 2.2480. Min Range: -2.2480

Max Act: 2.0083. Min Act: -0.0000

Data Index: 1609513 (Python Code)

Max Activating Token Index: 701

Text #12

Max Range: 2.2480. Min Range: -2.2480

Max Act: 1.8888. Min Act: -0.0000

Data Index: 1580307 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 2.2480. Min Range: -2.2480

Max Act: 1.9324. Min Act: -0.0001

Data Index: 1426526 (Python Code)

Max Activating Token Index: 376

Text #14

Max Range: 2.2480. Min Range: -2.2480

Max Act: 1.8278. Min Act: -0.0000

Data Index: 1428577 (Python Code)

Max Activating Token Index: 614

Text #15

Max Range: 2.2480. Min Range: -2.2480

Max Act: 1.8612. Min Act: -0.0000

Data Index: 1440434 (Python Code)

Max Activating Token Index: 320

Text #16

Max Range: 2.2480. Min Range: -2.2480

Max Act: 1.8604. Min Act: -0.0000

Data Index: 1643116 (Python Code)

Max Activating Token Index: 262

Text #17

Max Range: 2.2480. Min Range: -2.2480

Max Act: 1.8546. Min Act: -0.0000

Data Index: 1434486 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 2.2480. Min Range: -2.2480

Max Act: 1.7948. Min Act: -0.0001

Data Index: 1480275 (Python Code)

Max Activating Token Index: 107

Text #19

Max Range: 2.2480. Min Range: -2.2480

Max Act: 1.8380. Min Act: -0.0000

Data Index: 1626565 (Python Code)

Max Activating Token Index: 467