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

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

Neuron 2514 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.2463. Min Act: -0.0001

Data Index: 49842 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.0986. Min Act: -0.0001

Data Index: 1195601 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.1124. Min Act: -0.0001

Data Index: 1058693 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.0640. Min Act: -0.0001

Data Index: 61016 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.9712. Min Act: -0.0001

Data Index: 378954 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.9756. Min Act: -0.0001

Data Index: 297996 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 1.2463. Min Range: -1.2463

Max Act: 1.0412. Min Act: -0.0001

Data Index: 944651 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.9634. Min Act: -0.0001

Data Index: 564831 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.8864. Min Act: -0.0001

Data Index: 434569 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.8399. Min Act: -0.0001

Data Index: 133365 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.9046. Min Act: -0.0001

Data Index: 270530 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.8923. Min Act: -0.0001

Data Index: 380077 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.8350. Min Act: -0.0001

Data Index: 268304 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.9185. Min Act: -0.0001

Data Index: 815463 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.8113. Min Act: -0.0001

Data Index: 199866 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.8256. Min Act: -0.0001

Data Index: 901621 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.8848. Min Act: -0.0001

Data Index: 45436 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.8159. Min Act: -0.0001

Data Index: 912251 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.8806. Min Act: -0.0001

Data Index: 37683 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 1.2463. Min Range: -1.2463

Max Act: 0.8754. Min Act: -0.0001

Data Index: 236843 (C4 (Web Text))

Max Activating Token Index: 961