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

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

Neuron 829 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.2059. Min Act: -0.0000

Data Index: 451730 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1308355 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1938. Min Act: -0.0000

Data Index: 425724 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1878. Min Act: -0.0000

Data Index: 288017 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1765. Min Act: -0.0000

Data Index: 499647 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1698. Min Act: -0.0000

Data Index: 866127 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1656. Min Act: -0.0000

Data Index: 843837 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1670. Min Act: -0.0000

Data Index: 112543 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1585. Min Act: -0.0000

Data Index: 900833 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1612. Min Act: -0.0000

Data Index: 125534 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1500. Min Act: -0.0000

Data Index: 602047 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1259369 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1586. Min Act: -0.0000

Data Index: 178559 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1188583 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1560. Min Act: -0.0000

Data Index: 126064 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1368. Min Act: -0.0000

Data Index: 369830 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1129335 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1475. Min Act: -0.0000

Data Index: 331859 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1257366 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1007749 (C4 (Web Text))

Max Activating Token Index: 525