Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 390 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1290740 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0511. Min Act: -0.0003

Data Index: 346642 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0468. Min Act: -0.0003

Data Index: 107327 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0488. Min Act: -0.0003

Data Index: 186379 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1067525 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0445. Min Act: -0.0003

Data Index: 846657 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0468. Min Act: -0.0003

Data Index: 608056 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0465. Min Act: -0.0003

Data Index: 173953 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0458. Min Act: -0.0003

Data Index: 980862 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1308412 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0446. Min Act: -0.0003

Data Index: 272082 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0443. Min Act: -0.0003

Data Index: 184523 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0439. Min Act: -0.0004

Data Index: 1257214 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0434. Min Act: -0.0003

Data Index: 661990 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0434. Min Act: -0.0003

Data Index: 524405 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1253691 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0413. Min Act: -0.0003

Data Index: 94626 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1271828 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0418. Min Act: -0.0003

Data Index: 294883 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0436. Min Act: -0.0003

Data Index: 894344 (C4 (Web Text))

Max Activating Token Index: 209