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

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

Neuron 2017 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5618. Min Range: -3.5618

Max Act: 3.5618. Min Act: -0.0001

Data Index: 1027486 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 3.5618. Min Range: -3.5618

Max Act: 3.0900. Min Act: -0.0001

Data Index: 1095250 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 3.5618. Min Range: -3.5618

Max Act: 3.2511. Min Act: -0.0001

Data Index: 971110 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 3.5618. Min Range: -3.5618

Max Act: 3.3105. Min Act: -0.0000

Data Index: 452945 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 3.5618. Min Range: -3.5618

Max Act: 3.1342. Min Act: -0.0000

Data Index: 187208 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 3.5618. Min Range: -3.5618

Max Act: 3.4444. Min Act: -0.0001

Data Index: 791913 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 3.5618. Min Range: -3.5618

Max Act: 3.1478. Min Act: -0.0001

Data Index: 89835 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.8399. Min Act: -0.0001

Data Index: 16264 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.9043. Min Act: -0.0001

Data Index: 72959 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.5618. Min Range: -3.5618

Max Act: 3.1133. Min Act: -0.0001

Data Index: 92219 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 3.5618. Min Range: -3.5618

Max Act: 3.0707. Min Act: -0.0001

Data Index: 85118 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.7820. Min Act: -0.0001

Data Index: 670090 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.6332. Min Act: -0.0000

Data Index: 787887 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.6164. Min Act: -0.0001

Data Index: 376674 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.6215. Min Act: -0.0000

Data Index: 1052474 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.5934. Min Act: -0.0001

Data Index: 410279 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.5796. Min Act: -0.0001

Data Index: 198767 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.4084. Min Act: -0.0001

Data Index: 877893 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.6317. Min Act: -0.0001

Data Index: 84256 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 3.5618. Min Range: -3.5618

Max Act: 2.6142. Min Act: -0.0001

Data Index: 847825 (C4 (Web Text))

Max Activating Token Index: 259