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

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

Neuron 3418 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1291753 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1207700 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2338. Min Act: -0.0000

Data Index: 240671 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2257. Min Act: -0.0000

Data Index: 305398 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2307. Min Act: -0.0000

Data Index: 534753 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2171. Min Act: -0.0000

Data Index: 537492 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2182. Min Act: -0.0000

Data Index: 378783 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1094384 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1878. Min Act: -0.0000

Data Index: 439799 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1865. Min Act: -0.0000

Data Index: 474657 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.2033. Min Act: -0.0000

Data Index: 276185 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1933. Min Act: -0.0000

Data Index: 416380 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1918. Min Act: -0.0000

Data Index: 977311 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1909. Min Act: -0.0000

Data Index: 11947 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1963. Min Act: -0.0000

Data Index: 506580 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1912. Min Act: -0.0000

Data Index: 446550 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1903. Min Act: -0.0000

Data Index: 975609 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1960. Min Act: -0.0000

Data Index: 220145 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1828. Min Act: -0.0000

Data Index: 795577 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.2587. Min Range: -0.2587

Max Act: 0.1805. Min Act: -0.0000

Data Index: 959228 (C4 (Web Text))

Max Activating Token Index: 831