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

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

Neuron 2822 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.3175. Min Act: -0.0001

Data Index: 751349 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1895. Min Act: -0.0001

Data Index: 703272 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1399. Min Act: -0.0001

Data Index: 338630 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1165. Min Act: -0.0001

Data Index: 609709 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1448. Min Act: -0.0001

Data Index: 502575 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0770. Min Act: -0.0001

Data Index: 704756 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1397. Min Act: -0.0001

Data Index: 189520 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0327. Min Act: -0.0001

Data Index: 25973 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0386. Min Act: -0.0001

Data Index: 1197468 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1272. Min Act: -0.0001

Data Index: 37808 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1261. Min Act: -0.0001

Data Index: 845063 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9722. Min Act: -0.0001

Data Index: 832114 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.8761. Min Act: -0.0001

Data Index: 362591 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1027372 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0933. Min Act: -0.0001

Data Index: 345327 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1332. Min Act: -0.0001

Data Index: 1223930 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.7804. Min Act: -0.0001

Data Index: 494435 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9242. Min Act: -0.0001

Data Index: 707670 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9731. Min Act: -0.0001

Data Index: 340075 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9347. Min Act: -0.0001

Data Index: 705370 (C4 (Web Text))

Max Activating Token Index: 875