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

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

Neuron 4154 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: 1.5648. Min Range: -1.5648

Max Act: 1.5648. Min Act: -0.0000

Data Index: 1017360 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.5184. Min Act: -0.0000

Data Index: 524165 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.4619. Min Act: -0.0000

Data Index: 146009 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.4216. Min Act: -0.0000

Data Index: 1062855 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.4015. Min Act: -0.0000

Data Index: 1041655 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1085380 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.2304. Min Act: -0.0000

Data Index: 535055 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.2738. Min Act: -0.0000

Data Index: 1321322 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.1769. Min Act: -0.0000

Data Index: 1334112 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.2135. Min Act: -0.0000

Data Index: 405242 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.1551. Min Act: -0.0000

Data Index: 1069975 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.1152. Min Act: -0.0000

Data Index: 904493 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.1820. Min Act: -0.0000

Data Index: 1297293 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1222372 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1279094 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.0326. Min Act: -0.0000

Data Index: 778625 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.1204. Min Act: -0.0000

Data Index: 391044 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 1.5648. Min Range: -1.5648

Max Act: 0.9999. Min Act: -0.0000

Data Index: 322012 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.5648. Min Range: -1.5648

Max Act: 1.0351. Min Act: -0.0000

Data Index: 487491 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 1.5648. Min Range: -1.5648

Max Act: 0.9835. Min Act: -0.0000

Data Index: 787335 (C4 (Web Text))

Max Activating Token Index: 728