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

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

Neuron 1406 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1206. Min Range: -1.1206

Max Act: 1.1206. Min Act: -0.0001

Data Index: 1113015 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 1.1206. Min Range: -1.1206

Max Act: 1.0473. Min Act: -0.0001

Data Index: 1225482 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9934. Min Act: -0.0001

Data Index: 506190 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 1.1206. Min Range: -1.1206

Max Act: 1.0041. Min Act: -0.0001

Data Index: 333410 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9621. Min Act: -0.0001

Data Index: 402304 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 1.1206. Min Range: -1.1206

Max Act: 1.0801. Min Act: -0.0001

Data Index: 57263 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9913. Min Act: -0.0001

Data Index: 244070 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9924. Min Act: -0.0001

Data Index: 698914 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 1.1206. Min Range: -1.1206

Max Act: 1.0207. Min Act: -0.0001

Data Index: 80354 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9388. Min Act: -0.0001

Data Index: 866585 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9741. Min Act: -0.0001

Data Index: 642280 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9875. Min Act: -0.0001

Data Index: 560952 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9237. Min Act: -0.0001

Data Index: 1279863 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9517. Min Act: -0.0001

Data Index: 845245 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.8492. Min Act: -0.0001

Data Index: 1250796 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9122. Min Act: -0.0001

Data Index: 881818 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9074. Min Act: -0.0001

Data Index: 673191 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.9281. Min Act: -0.0001

Data Index: 904416 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.8936. Min Act: -0.0001

Data Index: 138467 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 1.1206. Min Range: -1.1206

Max Act: 0.8878. Min Act: -0.0001

Data Index: 994389 (C4 (Web Text))

Max Activating Token Index: 520