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

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

Neuron 635 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: 0.2072. Min Range: -0.2072

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1294284 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1962. Min Act: -0.0001

Data Index: 1336874 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1878 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1304303 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1764. Min Act: -0.0000

Data Index: 704550 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1753. Min Act: -0.0000

Data Index: 106657 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1817. Min Act: -0.0000

Data Index: 77253 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1639. Min Act: -0.0000

Data Index: 895578 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1695. Min Act: -0.0001

Data Index: 127987 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1547. Min Act: -0.0000

Data Index: 401486 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1696. Min Act: -0.0000

Data Index: 704362 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1592. Min Act: -0.0000

Data Index: 174687 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1570. Min Act: -0.0000

Data Index: 670836 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1540. Min Act: -0.0000

Data Index: 639115 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1103833 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1481. Min Act: -0.0001

Data Index: 734063 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1503. Min Act: -0.0000

Data Index: 440342 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1063574 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1221450 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1499. Min Act: -0.0000

Data Index: 86286 (C4 (Web Text))

Max Activating Token Index: 898