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

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

Neuron 1546 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.5639. Min Act: -0.0000

Data Index: 481667 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.4143. Min Act: -0.0000

Data Index: 193149 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.3588. Min Act: -0.0000

Data Index: 1133103 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.2568. Min Act: -0.0000

Data Index: 228378 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.2115. Min Act: -0.0000

Data Index: 182086 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.1990. Min Act: -0.0000

Data Index: 59583 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.1930. Min Act: -0.0000

Data Index: 782620 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.1150. Min Act: -0.0000

Data Index: 252659 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.0996. Min Act: -0.0000

Data Index: 453743 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.1635. Min Act: -0.0000

Data Index: 289440 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.1479. Min Act: -0.0000

Data Index: 807309 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.1327. Min Act: -0.0000

Data Index: 145137 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.1181. Min Act: -0.0000

Data Index: 224108 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.1305. Min Act: -0.0000

Data Index: 7243 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.0573. Min Act: -0.0000

Data Index: 182190 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.1238. Min Act: -0.0000

Data Index: 284374 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.0450. Min Act: -0.0000

Data Index: 496078 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.0879. Min Act: -0.0000

Data Index: 178136 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.0702. Min Act: -0.0000

Data Index: 258047 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 1.5639. Min Range: -1.5639

Max Act: 1.0632. Min Act: -0.0000

Data Index: 229966 (C4 (Web Text))

Max Activating Token Index: 116