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

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

Neuron 2451 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: 0.2663. Min Range: -0.2663

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1195916 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1033273 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.2118. Min Act: -0.0000

Data Index: 988531 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.2052. Min Act: -0.0000

Data Index: 974288 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1952. Min Act: -0.0000

Data Index: 262225 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1359690 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1307385 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1318264 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1186641 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1626. Min Act: -0.0000

Data Index: 737823 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1688. Min Act: -0.0000

Data Index: 415415 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1599. Min Act: -0.0000

Data Index: 210659 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1515. Min Act: -0.0000

Data Index: 708340 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1606. Min Act: -0.0000

Data Index: 657690 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1643. Min Act: -0.0000

Data Index: 389943 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1159798 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1050202 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1416. Min Act: -0.0000

Data Index: 187031 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1533. Min Act: -0.0000

Data Index: 714324 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.2663. Min Range: -0.2663

Max Act: 0.1548. Min Act: -0.0000

Data Index: 276318 (C4 (Web Text))

Max Activating Token Index: 825