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

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

Neuron 1687 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.1432. Min Act: -0.0000

Data Index: 744942 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.1658. Min Act: -0.0000

Data Index: 985687 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.1171. Min Act: -0.0000

Data Index: 911168 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1126376 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.0358. Min Act: 0.0000

Data Index: 647830 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.0269. Min Act: -0.0000

Data Index: 21572 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9943. Min Act: -0.0000

Data Index: 791140 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9954. Min Act: -0.0000

Data Index: 769147 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9037. Min Act: -0.0000

Data Index: 23852 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1275738 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.0119. Min Act: -0.0000

Data Index: 988616 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9527. Min Act: -0.0000

Data Index: 781763 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.8932. Min Act: -0.0000

Data Index: 987000 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1251499 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.8796. Min Act: -0.0000

Data Index: 287182 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1063725 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9281. Min Act: -0.0000

Data Index: 624255 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1266130 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9240. Min Act: -0.0000

Data Index: 343304 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1192245 (C4 (Web Text))

Max Activating Token Index: 312