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

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

Neuron 886 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: 3.0449. Min Range: -3.0449

Max Act: 3.0449. Min Act: -0.0001

Data Index: 649000 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 3.0449. Min Range: -3.0449

Max Act: 2.4380. Min Act: -0.0001

Data Index: 641333 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 3.0449. Min Range: -3.0449

Max Act: 2.3978. Min Act: -0.0001

Data Index: 503049 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 3.0449. Min Range: -3.0449

Max Act: 2.4312. Min Act: -0.0001

Data Index: 37387 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 3.0449. Min Range: -3.0449

Max Act: 2.0987. Min Act: -0.0001

Data Index: 1109290 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 3.0449. Min Range: -3.0449

Max Act: 2.1667. Min Act: -0.0001

Data Index: 980036 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.9651. Min Act: -0.0001

Data Index: 502017 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.9541. Min Act: -0.0001

Data Index: 778795 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 3.0449. Min Range: -3.0449

Max Act: 2.1375. Min Act: -0.0001

Data Index: 1015239 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.7295. Min Act: -0.0001

Data Index: 161533 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 3.0449. Min Range: -3.0449

Max Act: 2.0303. Min Act: -0.0001

Data Index: 600790 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.9595. Min Act: -0.0000

Data Index: 1251740 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.8169. Min Act: -0.0001

Data Index: 974654 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.9023. Min Act: -0.0001

Data Index: 77187 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.7833. Min Act: -0.0000

Data Index: 176524 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.8928. Min Act: -0.0001

Data Index: 847361 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.7656. Min Act: -0.0001

Data Index: 1249110 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.9146. Min Act: -0.0001

Data Index: 625279 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.8200. Min Act: -0.0000

Data Index: 836041 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 3.0449. Min Range: -3.0449

Max Act: 1.9147. Min Act: -0.0001

Data Index: 1089214 (C4 (Web Text))

Max Activating Token Index: 450