Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4726 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2493. Min Range: -2.2493

Max Act: 2.2493. Min Act: -0.0000

Data Index: 716760 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.9446. Min Act: -0.0000

Data Index: 342398 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.9143. Min Act: -0.0000

Data Index: 1438006 (Python Code)

Max Activating Token Index: 612

Text #3

Max Range: 2.2493. Min Range: -2.2493

Max Act: 2.0168. Min Act: -0.0000

Data Index: 118937 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.7771. Min Act: -0.0000

Data Index: 1393840 (Python Code)

Max Activating Token Index: 723

Text #5

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.6482. Min Act: -0.0000

Data Index: 1489641 (Python Code)

Max Activating Token Index: 965

Text #6

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.7931. Min Act: -0.0000

Data Index: 1470202 (Python Code)

Max Activating Token Index: 565

Text #7

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.6500. Min Act: -0.0000

Data Index: 1628246 (Python Code)

Max Activating Token Index: 858

Text #8

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.3737. Min Act: -0.0000

Data Index: 280422 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.4084. Min Act: -0.0000

Data Index: 1369028 (Python Code)

Max Activating Token Index: 468

Text #10

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.3029. Min Act: -0.0000

Data Index: 1599954 (Python Code)

Max Activating Token Index: 869

Text #11

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.2983. Min Act: -0.0000

Data Index: 1451191 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.1903. Min Act: -0.0000

Data Index: 143176 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1566466 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1423828 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1471277 (Python Code)

Max Activating Token Index: 192

Text #16

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.1824. Min Act: -0.0000

Data Index: 64916 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1082846 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.1257. Min Act: -0.0000

Data Index: 2014 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 2.2493. Min Range: -2.2493

Max Act: 1.1306. Min Act: -0.0000

Data Index: 783743 (C4 (Web Text))

Max Activating Token Index: 548