Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 500 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.8986. Min Act: -0.0000

Data Index: 1314952 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.9603. Min Act: -0.0000

Data Index: 1255063 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.7066. Min Act: -0.0000

Data Index: 899060 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.5175. Min Act: -0.0000

Data Index: 734627 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.4964. Min Act: -0.0000

Data Index: 851179 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.8633. Min Act: -0.0000

Data Index: 569364 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.4924. Min Act: -0.0000

Data Index: 1105821 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.5751. Min Act: -0.0000

Data Index: 755192 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.5238. Min Act: -0.0000

Data Index: 204126 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.3678. Min Act: -0.0000

Data Index: 1031204 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.3546. Min Act: -0.0000

Data Index: 335235 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.3670. Min Act: -0.0000

Data Index: 198573 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.2857. Min Act: -0.0000

Data Index: 1249877 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.2676. Min Act: -0.0000

Data Index: 862573 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.1232. Min Act: -0.0000

Data Index: 1000253 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.3545. Min Act: -0.0000

Data Index: 421725 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.1332. Min Act: -0.0000

Data Index: 608538 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.4663. Min Act: -0.0000

Data Index: 592568 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.3310. Min Act: -0.0000

Data Index: 270603 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 2.9603. Min Range: -2.9603

Max Act: 2.3350. Min Act: -0.0000

Data Index: 1296909 (C4 (Web Text))

Max Activating Token Index: 255