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

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

Neuron 1524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.6267. Min Act: -0.0000

Data Index: 1159385 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.6353. Min Act: -0.0000

Data Index: 565130 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.1349. Min Act: -0.0000

Data Index: 826619 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.1923. Min Act: -0.0000

Data Index: 842949 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.0462. Min Act: -0.0000

Data Index: 759026 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.0552. Min Act: -0.0000

Data Index: 866561 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.0492. Min Act: -0.0000

Data Index: 866229 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1128798 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.6353. Min Range: -1.6353

Max Act: 1.0740. Min Act: -0.0000

Data Index: 590442 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.9638. Min Act: -0.0000

Data Index: 668543 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.8052. Min Act: -0.0000

Data Index: 491722 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1097393 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.9539. Min Act: -0.0000

Data Index: 80377 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1243538 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.9125. Min Act: -0.0000

Data Index: 725078 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.9040. Min Act: -0.0000

Data Index: 175841 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1284624 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.9548. Min Act: -0.0000

Data Index: 386141 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1346580 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.6353. Min Range: -1.6353

Max Act: 0.8397. Min Act: -0.0000

Data Index: 204731 (C4 (Web Text))

Max Activating Token Index: 891