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

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

Neuron 3487 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: 1.6713. Min Range: -1.6713

Max Act: 1.6713. Min Act: -0.0001

Data Index: 353927 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.5350. Min Act: -0.0001

Data Index: 239845 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.5353. Min Act: -0.0001

Data Index: 337858 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.5380. Min Act: -0.0001

Data Index: 1038796 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.5269. Min Act: -0.0001

Data Index: 1134298 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.4273. Min Act: -0.0001

Data Index: 1223192 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.5093. Min Act: -0.0001

Data Index: 1255718 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.5127. Min Act: -0.0001

Data Index: 188575 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.4284. Min Act: -0.0001

Data Index: 60981 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.4245. Min Act: -0.0001

Data Index: 378870 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.2310. Min Act: -0.0001

Data Index: 100012 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3621. Min Act: -0.0001

Data Index: 1318448 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.4648. Min Act: -0.0001

Data Index: 824637 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.2795. Min Act: -0.0001

Data Index: 719441 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3290. Min Act: -0.0001

Data Index: 151250 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3343. Min Act: -0.0001

Data Index: 922143 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3453. Min Act: -0.0001

Data Index: 483236 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.1526. Min Act: -0.0001

Data Index: 93983 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.2709. Min Act: -0.0001

Data Index: 775995 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.2192. Min Act: -0.0001

Data Index: 1238079 (C4 (Web Text))

Max Activating Token Index: 462