Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2967 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1154002 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1856. Min Act: -0.0001

Data Index: 564243 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1695. Min Act: -0.0001

Data Index: 181050 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1000635 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1276704 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1683. Min Act: -0.0001

Data Index: 548717 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1576. Min Act: -0.0001

Data Index: 483364 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1030251 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1656. Min Act: -0.0001

Data Index: 652015 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1424. Min Act: -0.0001

Data Index: 268846 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1532. Min Act: -0.0000

Data Index: 163591 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1631. Min Act: -0.0001

Data Index: 512923 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1249276 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1555. Min Act: -0.0000

Data Index: 76064 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1503. Min Act: -0.0000

Data Index: 750157 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1484. Min Act: -0.0001

Data Index: 645770 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1493. Min Act: -0.0001

Data Index: 769248 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1227683 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1488. Min Act: -0.0001

Data Index: 96427 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1457. Min Act: -0.0000

Data Index: 827149 (C4 (Web Text))

Max Activating Token Index: 1020