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

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

Neuron 3518 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.2124. Min Act: -0.0001

Data Index: 243743 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.2062. Min Act: -0.0001

Data Index: 1044722 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1981. Min Act: -0.0001

Data Index: 918942 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.2047. Min Act: -0.0001

Data Index: 136728 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1906. Min Act: -0.0000

Data Index: 582454 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1838. Min Act: -0.0000

Data Index: 225598 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1822. Min Act: -0.0000

Data Index: 49100 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1652. Min Act: -0.0000

Data Index: 138056 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1831. Min Act: -0.0001

Data Index: 1217921 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1878. Min Act: -0.0001

Data Index: 301352 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1682. Min Act: -0.0000

Data Index: 11576 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1749. Min Act: -0.0001

Data Index: 296334 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1193883 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1575. Min Act: -0.0001

Data Index: 187792 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1088947 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1590. Min Act: -0.0000

Data Index: 163682 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1516. Min Act: -0.0001

Data Index: 850166 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1490. Min Act: -0.0001

Data Index: 970424 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1540. Min Act: -0.0000

Data Index: 175703 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.2124. Min Range: -0.2124

Max Act: 0.1392. Min Act: -0.0000

Data Index: 980479 (C4 (Web Text))

Max Activating Token Index: 227