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

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

Neuron 4642 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: 1.2342. Min Range: -1.2342

Max Act: 1.2026. Min Act: -0.0000

Data Index: 22290 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.2342. Min Range: -1.2342

Max Act: 1.1633. Min Act: -0.0000

Data Index: 895665 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 1.2342. Min Range: -1.2342

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1266237 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 1.2342. Min Range: -1.2342

Max Act: 1.2342. Min Act: -0.0000

Data Index: 5760 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.2342. Min Range: -1.2342

Max Act: 1.0559. Min Act: -0.0000

Data Index: 832798 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 1.2342. Min Range: -1.2342

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1126887 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.9657. Min Act: -0.0000

Data Index: 550424 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1103970 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.9074. Min Act: -0.0000

Data Index: 438325 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8852. Min Act: -0.0000

Data Index: 876755 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1263904 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8661. Min Act: -0.0000

Data Index: 497682 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8625. Min Act: -0.0000

Data Index: 79501 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8629. Min Act: -0.0000

Data Index: 155280 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1334750 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8817. Min Act: -0.0000

Data Index: 597158 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1341483 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1132598 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1001463 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 1.2342. Min Range: -1.2342

Max Act: 0.8168. Min Act: -0.0000

Data Index: 52121 (C4 (Web Text))

Max Activating Token Index: 648