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

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

Neuron 5050 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.8123. Min Act: -0.0000

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.8449. Min Act: -0.0000

Data Index: 57082 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1209318 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.8528. Min Act: -0.0000

Data Index: 730425 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.7109. Min Act: -0.0000

Data Index: 999600 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.7504. Min Act: -0.0000

Data Index: 612480 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6814. Min Act: -0.0000

Data Index: 54053 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6414. Min Act: -0.0000

Data Index: 596495 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1147903 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6551. Min Act: -0.0000

Data Index: 187075 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5861. Min Act: -0.0000

Data Index: 533683 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6208. Min Act: -0.0000

Data Index: 262192 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1226279 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6089. Min Act: -0.0000

Data Index: 675069 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1032437 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1340413 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5952. Min Act: -0.0000

Data Index: 309779 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1320038 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5784. Min Act: -0.0000

Data Index: 64070 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.8528. Min Range: -0.8528

Max Act: 0.5530. Min Act: -0.0000

Data Index: 75594 (C4 (Web Text))

Max Activating Token Index: 99