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

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

Neuron 3417 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.2385. Min Act: -0.0000

Data Index: 1193084 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1124. Min Act: -0.0000

Data Index: 944806 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1110710 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1149358 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.8730. Min Act: -0.0000

Data Index: 799872 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.8448. Min Act: -0.0000

Data Index: 636393 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1209923 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.8598. Min Act: -0.0000

Data Index: 770363 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9089. Min Act: -0.0000

Data Index: 763004 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1317914 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.8668. Min Act: -0.0000

Data Index: 983615 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.8663. Min Act: -0.0000

Data Index: 205700 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.8343. Min Act: -0.0000

Data Index: 214604 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.8125. Min Act: -0.0000

Data Index: 717840 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.8157. Min Act: -0.0000

Data Index: 851019 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.7686. Min Act: -0.0000

Data Index: 979892 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.7749. Min Act: -0.0000

Data Index: 739030 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1195115 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.7822. Min Act: -0.0000

Data Index: 553833 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1123211 (C4 (Web Text))

Max Activating Token Index: 41