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

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

Neuron 1968 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.7317. Min Act: -0.0000

Data Index: 618186 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.4023. Min Act: -0.0000

Data Index: 1126120 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.3359. Min Act: -0.0000

Data Index: 758810 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2403. Min Act: -0.0000

Data Index: 12111 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.3046. Min Act: -0.0000

Data Index: 1096790 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2973. Min Act: -0.0000

Data Index: 882143 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.3245. Min Act: -0.0000

Data Index: 713779 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2835. Min Act: -0.0000

Data Index: 415233 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2033. Min Act: -0.0000

Data Index: 1155500 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2475. Min Act: -0.0000

Data Index: 1314260 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.1354. Min Act: -0.0000

Data Index: 618784 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2190. Min Act: -0.0000

Data Index: 228142 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1234297 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.2473. Min Act: -0.0000

Data Index: 111508 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.1131. Min Act: -0.0000

Data Index: 88623 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.1820. Min Act: -0.0000

Data Index: 776585 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1012699 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.0973. Min Act: -0.0000

Data Index: 1071852 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.1720. Min Act: -0.0000

Data Index: 204808 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 1.7317. Min Range: -1.7317

Max Act: 1.1249. Min Act: -0.0000

Data Index: 1155700 (C4 (Web Text))

Max Activating Token Index: 43