Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3922 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.5438. Min Act: -0.0001

Data Index: 716099 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.5628. Min Act: -0.0001

Data Index: 901753 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.6309. Min Act: -0.0001

Data Index: 753962 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.5396. Min Act: -0.0001

Data Index: 912880 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1900. Min Act: -0.0001

Data Index: 1040229 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.2693. Min Act: -0.0001

Data Index: 639605 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1644. Min Act: -0.0001

Data Index: 916098 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.2897. Min Act: -0.0001

Data Index: 1147643 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1920. Min Act: -0.0001

Data Index: 938138 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1759. Min Act: -0.0001

Data Index: 1101912 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1072. Min Act: -0.0001

Data Index: 1149349 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1093. Min Act: -0.0001

Data Index: 290698 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1512. Min Act: -0.0001

Data Index: 705209 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1662. Min Act: -0.0001

Data Index: 515481 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1319. Min Act: -0.0001

Data Index: 1334748 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1204. Min Act: -0.0001

Data Index: 754032 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.2170. Min Act: -0.0001

Data Index: 614305 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1053. Min Act: -0.0001

Data Index: 1072839 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1744. Min Act: -0.0001

Data Index: 425986 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.1118. Min Act: -0.0001

Data Index: 1242337 (C4 (Web Text))

Max Activating Token Index: 217