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

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

Neuron 5531 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2780. Min Act: -0.0000

Data Index: 223901 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2301. Min Act: -0.0000

Data Index: 896744 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1050310 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2123. Min Act: -0.0000

Data Index: 66406 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1320741 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1259013 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1305321 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1128509 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1867. Min Act: -0.0000

Data Index: 857278 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1703. Min Act: -0.0000

Data Index: 92152 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1055702 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1637. Min Act: 0.0000

Data Index: 281633 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1033565 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1191156 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1527. Min Act: -0.0000

Data Index: 331130 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1461. Min Act: -0.0000

Data Index: 278265 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1549. Min Act: -0.0000

Data Index: 600383 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1485. Min Act: -0.0000

Data Index: 137047 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1486. Min Act: -0.0000

Data Index: 85380 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.2780. Min Range: -0.2780

Max Act: 0.1528. Min Act: -0.0000

Data Index: 153834 (C4 (Web Text))

Max Activating Token Index: 989