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

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

Neuron 300 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: 0.2443. Min Range: -0.2443

Max Act: 0.2443. Min Act: -0.0001

Data Index: 1110900 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.2292. Min Act: -0.0000

Data Index: 667252 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.2282. Min Act: -0.0000

Data Index: 214395 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1045802 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.2182. Min Act: -0.0001

Data Index: 645985 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1999. Min Act: -0.0001

Data Index: 610194 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.2147. Min Act: -0.0000

Data Index: 316399 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1086415 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1824. Min Act: -0.0000

Data Index: 557560 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1870. Min Act: -0.0000

Data Index: 828483 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1880. Min Act: -0.0000

Data Index: 320908 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1041900 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1977. Min Act: -0.0001

Data Index: 2558 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1904. Min Act: -0.0000

Data Index: 368788 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1155110 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1184785 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1799. Min Act: -0.0000

Data Index: 296627 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1852. Min Act: -0.0000

Data Index: 588346 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1858. Min Act: -0.0000

Data Index: 271451 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.2443. Min Range: -0.2443

Max Act: 0.1783. Min Act: -0.0000

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 508