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

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

Neuron 1775 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5434. Min Act: -0.0000

Data Index: 610378 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5006. Min Act: -0.0000

Data Index: 464337 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5266. Min Act: -0.0000

Data Index: 2592 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1329901 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4928. Min Act: -0.0000

Data Index: 850517 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4723. Min Act: -0.0000

Data Index: 568660 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1100647 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4960. Min Act: -0.0000

Data Index: 889846 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1222580 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4728. Min Act: -0.0000

Data Index: 725198 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4397. Min Act: -0.0000

Data Index: 661521 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3994. Min Act: -0.0000

Data Index: 808172 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5283. Min Act: -0.0000

Data Index: 12936 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4398. Min Act: -0.0000

Data Index: 9230 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4545. Min Act: -0.0000

Data Index: 388723 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4188. Min Act: -0.0000

Data Index: 10449 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1084811 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1208120 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4298. Min Act: -0.0000

Data Index: 422628 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1022643 (C4 (Web Text))

Max Activating Token Index: 132