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

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

Neuron 1857 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: 3.1511. Min Range: -3.1511

Max Act: 3.1511. Min Act: -0.0001

Data Index: 880246 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9650. Min Act: -0.0001

Data Index: 1327568 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.6635. Min Act: -0.0001

Data Index: 1005704 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.5156. Min Act: -0.0001

Data Index: 900159 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.4368. Min Act: -0.0001

Data Index: 932882 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.5701. Min Act: -0.0001

Data Index: 142526 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.5230. Min Act: -0.0001

Data Index: 1297571 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.5936. Min Act: -0.0001

Data Index: 55869 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.5839. Min Act: -0.0001

Data Index: 616839 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.4489. Min Act: -0.0001

Data Index: 1239424 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.3476. Min Act: -0.0001

Data Index: 757765 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.1603. Min Act: -0.0001

Data Index: 881625 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.3845. Min Act: -0.0001

Data Index: 188359 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.0861. Min Act: -0.0001

Data Index: 130958 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.1328. Min Act: -0.0001

Data Index: 843080 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.0135. Min Act: -0.0001

Data Index: 311508 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.1130. Min Act: -0.0001

Data Index: 399031 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.1882. Min Act: -0.0001

Data Index: 1321707 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 3.1511. Min Range: -3.1511

Max Act: 1.9920. Min Act: -0.0001

Data Index: 803411 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.1872. Min Act: -0.0001

Data Index: 970883 (C4 (Web Text))

Max Activating Token Index: 932