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

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

Neuron 4772 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.3448. Min Act: -0.0000

Data Index: 708822 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2561. Min Act: -0.0000

Data Index: 586123 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2351. Min Act: -0.0000

Data Index: 909045 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2335. Min Act: -0.0000

Data Index: 531860 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2291. Min Act: -0.0000

Data Index: 697934 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2036. Min Act: -0.0000

Data Index: 398978 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2160. Min Act: -0.0001

Data Index: 169726 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1196545 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2017. Min Act: -0.0000

Data Index: 16282 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1947. Min Act: -0.0000

Data Index: 311133 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1903. Min Act: -0.0000

Data Index: 588345 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1343111 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1278364 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1919. Min Act: -0.0000

Data Index: 336130 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1696. Min Act: -0.0000

Data Index: 603167 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1867. Min Act: -0.0000

Data Index: 773109 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1806. Min Act: -0.0000

Data Index: 837259 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1682. Min Act: -0.0000

Data Index: 998534 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1770. Min Act: -0.0000

Data Index: 833573 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.3448. Min Range: -0.3448

Max Act: 0.1894. Min Act: -0.0001

Data Index: 979380 (C4 (Web Text))

Max Activating Token Index: 774