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

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

Neuron 2304 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1831. Min Range: -1.1831

Max Act: 1.1831. Min Act: -0.0001

Data Index: 152667 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 1.1831. Min Range: -1.1831

Max Act: 1.0421. Min Act: -0.0001

Data Index: 762369 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.9230. Min Act: -0.0001

Data Index: 1194431 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.1831. Min Range: -1.1831

Max Act: 1.0556. Min Act: -0.0001

Data Index: 913417 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 1.1831. Min Range: -1.1831

Max Act: 1.0881. Min Act: -0.0001

Data Index: 711847 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 1.1831. Min Range: -1.1831

Max Act: 1.0231. Min Act: -0.0001

Data Index: 365711 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.1831. Min Range: -1.1831

Max Act: 1.0264. Min Act: -0.0001

Data Index: 1278209 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.1831. Min Range: -1.1831

Max Act: 1.0289. Min Act: -0.0001

Data Index: 404566 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 1.1831. Min Range: -1.1831

Max Act: 1.0467. Min Act: -0.0001

Data Index: 1012345 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.9271. Min Act: -0.0001

Data Index: 161463 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.9705. Min Act: -0.0001

Data Index: 922212 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.9672. Min Act: -0.0001

Data Index: 343453 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.9521. Min Act: -0.0001

Data Index: 229961 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.8795. Min Act: -0.0001

Data Index: 983183 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.9696. Min Act: -0.0001

Data Index: 178598 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.9596. Min Act: -0.0001

Data Index: 221618 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.8304. Min Act: -0.0001

Data Index: 914322 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.9632. Min Act: -0.0001

Data Index: 732738 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.9312. Min Act: -0.0001

Data Index: 1140736 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 1.1831. Min Range: -1.1831

Max Act: 0.9229. Min Act: -0.0001

Data Index: 509915 (C4 (Web Text))

Max Activating Token Index: 825