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

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

Neuron 646 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.2890. Min Act: -0.0001

Data Index: 909745 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.2530. Min Act: -0.0001

Data Index: 1200278 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.2523. Min Act: -0.0001

Data Index: 475563 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.1888. Min Act: -0.0001

Data Index: 300413 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.2440. Min Act: -0.0001

Data Index: 1042880 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.1012. Min Act: -0.0001

Data Index: 489080 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.1854. Min Act: -0.0001

Data Index: 910143 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.2165. Min Act: -0.0001

Data Index: 97728 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.1364. Min Act: -0.0001

Data Index: 49974 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.0627. Min Act: -0.0001

Data Index: 760454 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.1621. Min Act: -0.0001

Data Index: 1035032 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.1702. Min Act: -0.0001

Data Index: 419582 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.0405. Min Act: -0.0001

Data Index: 1180748 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.1412. Min Act: -0.0001

Data Index: 898913 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.0854. Min Act: -0.0001

Data Index: 1032955 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.0486. Min Act: -0.0001

Data Index: 1300436 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.0803. Min Act: -0.0001

Data Index: 1019770 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.0643. Min Act: -0.0001

Data Index: 910411 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.0479. Min Act: -0.0001

Data Index: 554264 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 1.2890. Min Range: -1.2890

Max Act: 1.0455. Min Act: -0.0001

Data Index: 41255 (C4 (Web Text))

Max Activating Token Index: 31