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

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

Neuron 3792 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: 0.5626. Min Range: -0.5626

Max Act: 0.5626. Min Act: -0.0000

Data Index: 270072 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1184006 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.5164. Min Act: -0.0000

Data Index: 404256 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4615. Min Act: -0.0000

Data Index: 457532 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4771. Min Act: -0.0000

Data Index: 842163 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4322. Min Act: -0.0000

Data Index: 740615 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4321. Min Act: -0.0000

Data Index: 888432 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4437. Min Act: -0.0000

Data Index: 896069 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4357. Min Act: -0.0000

Data Index: 819394 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4625. Min Act: -0.0000

Data Index: 144259 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4300. Min Act: -0.0000

Data Index: 254617 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4007. Min Act: -0.0000

Data Index: 897922 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4389. Min Act: -0.0000

Data Index: 621759 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4362. Min Act: -0.0000

Data Index: 163784 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4305. Min Act: -0.0000

Data Index: 310701 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4487. Min Act: -0.0000

Data Index: 441660 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1208722 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4357. Min Act: -0.0000

Data Index: 999095 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4295. Min Act: -0.0000

Data Index: 417169 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.5626. Min Range: -0.5626

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1042453 (C4 (Web Text))

Max Activating Token Index: 295