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

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

Neuron 2436 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9306. Min Act: -0.0001

Data Index: 795219 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9246. Min Act: -0.0001

Data Index: 181804 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9278. Min Act: -0.0001

Data Index: 752613 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9161. Min Act: -0.0001

Data Index: 533829 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9276. Min Act: -0.0001

Data Index: 1312223 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8987. Min Act: -0.0001

Data Index: 966784 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8960. Min Act: -0.0001

Data Index: 515263 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8835. Min Act: -0.0001

Data Index: 406641 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8838. Min Act: -0.0001

Data Index: 376267 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8427. Min Act: -0.0001

Data Index: 565021 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8158. Min Act: -0.0001

Data Index: 513563 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8136. Min Act: -0.0001

Data Index: 873719 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8053. Min Act: -0.0001

Data Index: 128789 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8443. Min Act: -0.0001

Data Index: 416649 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7916. Min Act: -0.0001

Data Index: 174320 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8101. Min Act: -0.0001

Data Index: 216329 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7858. Min Act: -0.0001

Data Index: 594718 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8087. Min Act: -0.0001

Data Index: 647858 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8172. Min Act: -0.0001

Data Index: 370434 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7852. Min Act: -0.0001

Data Index: 201004 (C4 (Web Text))

Max Activating Token Index: 328