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

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

Neuron 5586 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2712. Min Act: -0.0000

Data Index: 623699 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1172607 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2349. Min Act: -0.0000

Data Index: 557400 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2364. Min Act: -0.0000

Data Index: 99291 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2317. Min Act: -0.0000

Data Index: 490653 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2160. Min Act: -0.0000

Data Index: 232136 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2194. Min Act: -0.0000

Data Index: 242236 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1176305 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2114. Min Act: -0.0000

Data Index: 353852 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1774. Min Act: -0.0000

Data Index: 795964 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1937. Min Act: -0.0000

Data Index: 388980 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1863. Min Act: -0.0000

Data Index: 723226 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1923. Min Act: -0.0000

Data Index: 448092 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1005308 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1000570 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1299825 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1848. Min Act: -0.0000

Data Index: 371722 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1770. Min Act: -0.0000

Data Index: 886400 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1821. Min Act: -0.0000

Data Index: 517288 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1241116 (C4 (Web Text))

Max Activating Token Index: 456