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

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

Neuron 4198 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2532. Min Range: -1.2532

Max Act: 1.2532. Min Act: -0.0000

Data Index: 53384 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.2532. Min Range: -1.2532

Max Act: 1.0626. Min Act: -0.0000

Data Index: 85714 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 1.2532. Min Range: -1.2532

Max Act: 1.0492. Min Act: 0.0000

Data Index: 136042 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.2532. Min Range: -1.2532

Max Act: 1.0328. Min Act: -0.0000

Data Index: 614281 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.2532. Min Range: -1.2532

Max Act: 1.0559. Min Act: -0.0000

Data Index: 80151 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.9238. Min Act: -0.0000

Data Index: 329679 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1238464 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.8865. Min Act: 0.0000

Data Index: 1196306 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.9291. Min Act: -0.0000

Data Index: 904338 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.8789. Min Act: -0.0000

Data Index: 173244 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.8804. Min Act: -0.0000

Data Index: 852882 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1249663 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7733. Min Act: -0.0000

Data Index: 188798 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1078212 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7867. Min Act: -0.0000

Data Index: 401152 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7765. Min Act: -0.0000

Data Index: 790108 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7630. Min Act: -0.0000

Data Index: 113982 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.6591. Min Act: -0.0000

Data Index: 813191 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.6162. Min Act: -0.0000

Data Index: 435264 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 1.2532. Min Range: -1.2532

Max Act: 0.7333. Min Act: -0.0000

Data Index: 180350 (C4 (Web Text))

Max Activating Token Index: 197