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

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

Neuron 2660 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.5617. Min Act: -0.0000

Data Index: 1361295 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.4461. Min Act: -0.0000

Data Index: 1499248 (Python Code)

Max Activating Token Index: 680

Text #2

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3574. Min Act: -0.0000

Data Index: 193600 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3251. Min Act: -0.0000

Data Index: 422681 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3684. Min Act: -0.0000

Data Index: 273710 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3164. Min Act: -0.0000

Data Index: 194870 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1458189 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.4713. Min Act: -0.0000

Data Index: 132292 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.4659. Min Act: -0.0000

Data Index: 1083986 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.4984. Min Act: -0.0000

Data Index: 1108927 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3563. Min Act: -0.0000

Data Index: 110076 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1107379 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3396. Min Act: -0.0000

Data Index: 358385 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3282. Min Act: -0.0000

Data Index: 398743 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1513960 (Python Code)

Max Activating Token Index: 758

Text #15

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3166. Min Act: -0.0000

Data Index: 542748 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.2492. Min Act: -0.0000

Data Index: 490775 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3537. Min Act: -0.0000

Data Index: 287472 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3086. Min Act: -0.0000

Data Index: 1078968 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 1.5617. Min Range: -1.5617

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1582916 (Python Code)

Max Activating Token Index: 406