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

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

Neuron 2722 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.4572. Min Act: -0.0002

Data Index: 264839 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.2680. Min Act: -0.0002

Data Index: 990661 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3973. Min Act: -0.0002

Data Index: 619428 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1862. Min Act: -0.0002

Data Index: 583903 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3165. Min Act: -0.0002

Data Index: 432717 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.2049. Min Act: -0.0002

Data Index: 289555 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3893. Min Act: -0.0002

Data Index: 629553 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.2601. Min Act: -0.0002

Data Index: 1118269 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3773. Min Act: -0.0002

Data Index: 855217 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3078. Min Act: -0.0002

Data Index: 825136 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.2222. Min Act: -0.0002

Data Index: 506659 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1245. Min Act: -0.0002

Data Index: 1302353 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3251. Min Act: -0.0002

Data Index: 410268 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3396. Min Act: -0.0002

Data Index: 641332 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.2622. Min Act: -0.0002

Data Index: 999808 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1615. Min Act: -0.0002

Data Index: 339301 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1615. Min Act: -0.0002

Data Index: 1090380 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3759. Min Act: -0.0002

Data Index: 1352234 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.3204. Min Act: -0.0002

Data Index: 917570 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.4572. Min Range: -1.4572

Max Act: 1.1395. Min Act: -0.0002

Data Index: 953027 (C4 (Web Text))

Max Activating Token Index: 209