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

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

Neuron 5035 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.1152. Min Act: -0.0000

Data Index: 402816 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1258286 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.1200. Min Act: -0.0000

Data Index: 870478 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1003080 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.0651. Min Act: -0.0000

Data Index: 111632 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9869. Min Act: -0.0000

Data Index: 481689 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1055385 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9246. Min Act: -0.0000

Data Index: 909067 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9031. Min Act: -0.0000

Data Index: 731845 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1313370 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8761. Min Act: -0.0000

Data Index: 813091 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8746. Min Act: -0.0000

Data Index: 625288 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7974. Min Act: -0.0000

Data Index: 214810 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1068936 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8328. Min Act: 0.0000

Data Index: 782169 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8031. Min Act: -0.0000

Data Index: 197873 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8029. Min Act: -0.0000

Data Index: 474643 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7924. Min Act: -0.0000

Data Index: 236794 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1224090 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7857. Min Act: -0.0000

Data Index: 921808 (C4 (Web Text))

Max Activating Token Index: 896