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

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

Neuron 730 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.2167. Min Act: -0.0000

Data Index: 368349 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1803. Min Act: -0.0000

Data Index: 386922 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 1.2167. Min Range: -1.2167

Max Act: 1.1354. Min Act: -0.0000

Data Index: 273084 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.8176. Min Act: -0.0000

Data Index: 830014 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.8269. Min Act: -0.0000

Data Index: 358619 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.8204. Min Act: -0.0000

Data Index: 897646 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.9669. Min Act: -0.0000

Data Index: 595066 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1156445 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.6813. Min Act: -0.0000

Data Index: 224785 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1219877 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7055. Min Act: -0.0000

Data Index: 102189 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7696. Min Act: -0.0000

Data Index: 345515 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7408. Min Act: -0.0000

Data Index: 761213 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7085. Min Act: -0.0000

Data Index: 518016 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7582. Min Act: -0.0000

Data Index: 278789 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7474. Min Act: -0.0000

Data Index: 1022723 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.6160. Min Act: -0.0000

Data Index: 525147 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7049. Min Act: -0.0000

Data Index: 544540 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7318. Min Act: -0.0000

Data Index: 681081 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 1.2167. Min Range: -1.2167

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1294699 (C4 (Web Text))

Max Activating Token Index: 730