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

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

Neuron 3440 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: -0.0000

Data Index: 992416 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1806. Min Act: -0.0000

Data Index: 832145 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1872. Min Act: -0.0000

Data Index: 213394 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1004487 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1720. Min Act: -0.0000

Data Index: 156660 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1697. Min Act: -0.0001

Data Index: 1052818 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1671. Min Act: -0.0000

Data Index: 198385 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1617. Min Act: -0.0001

Data Index: 346682 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1186332 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1227511 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1550. Min Act: -0.0000

Data Index: 111323 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1545. Min Act: -0.0000

Data Index: 708551 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1539. Min Act: -0.0000

Data Index: 652602 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1684. Min Act: -0.0000

Data Index: 663660 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1582. Min Act: -0.0000

Data Index: 759964 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1332121 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1515. Min Act: -0.0000

Data Index: 578226 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1496. Min Act: -0.0000

Data Index: 550196 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1541. Min Act: -0.0001

Data Index: 327071 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1510. Min Act: -0.0001

Data Index: 633069 (C4 (Web Text))

Max Activating Token Index: 227