Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0626. Min Act: -0.0001

Data Index: 81292 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0663. Min Act: -0.0001

Data Index: 808261 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0631. Min Act: -0.0001

Data Index: 703968 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0516. Min Act: -0.0001

Data Index: 59853 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0599. Min Act: -0.0001

Data Index: 913880 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0621. Min Act: -0.0001

Data Index: 207328 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0554. Min Act: -0.0001

Data Index: 392835 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0587. Min Act: -0.0001

Data Index: 552915 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0595. Min Act: -0.0001

Data Index: 274784 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0489. Min Act: -0.0001

Data Index: 96743 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1178102 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0554. Min Act: -0.0001

Data Index: 375895 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0534. Min Act: -0.0001

Data Index: 668756 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0530. Min Act: -0.0002

Data Index: 511612 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1075831 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0561. Min Act: -0.0001

Data Index: 926309 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1206654 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1283053 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1214901 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0480. Min Act: -0.0001

Data Index: 880257 (C4 (Web Text))

Max Activating Token Index: 576