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

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

Neuron 1064 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8842. Min Act: -0.0000

Data Index: 734987 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8240. Min Act: -0.0000

Data Index: 612957 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8044. Min Act: -0.0000

Data Index: 177931 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8901. Min Act: -0.0000

Data Index: 639354 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8476. Min Act: -0.0000

Data Index: 540566 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7149. Min Act: -0.0000

Data Index: 327817 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6929. Min Act: -0.0000

Data Index: 751427 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6240. Min Act: -0.0000

Data Index: 757943 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7079. Min Act: -0.0000

Data Index: 177210 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7186. Min Act: -0.0000

Data Index: 906781 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1100731 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6644. Min Act: -0.0000

Data Index: 934749 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1254002 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6731. Min Act: -0.0000

Data Index: 298297 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1132244 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6361. Min Act: -0.0000

Data Index: 584328 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6165. Min Act: -0.0000

Data Index: 625049 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6360. Min Act: -0.0000

Data Index: 947918 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6353. Min Act: -0.0000

Data Index: 795832 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6278. Min Act: -0.0000

Data Index: 879310 (C4 (Web Text))

Max Activating Token Index: 381