Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1448 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1934. Min Act: -0.0001

Data Index: 926625 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1879. Min Act: -0.0001

Data Index: 1233697 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1723. Min Act: -0.0001

Data Index: 150657 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1802. Min Act: -0.0001

Data Index: 980829 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1759. Min Act: -0.0001

Data Index: 25029 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1160630 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1572. Min Act: -0.0001

Data Index: 730291 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1063875 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1624. Min Act: -0.0001

Data Index: 104582 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1611. Min Act: -0.0001

Data Index: 871366 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1598. Min Act: -0.0001

Data Index: 380101 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1536. Min Act: -0.0001

Data Index: 315622 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1157102 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1558. Min Act: -0.0000

Data Index: 352153 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1501. Min Act: -0.0001

Data Index: 14350 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1539. Min Act: -0.0001

Data Index: 339092 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1176712 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1533. Min Act: -0.0001

Data Index: 206517 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1476. Min Act: -0.0001

Data Index: 3302 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1523. Min Act: -0.0001

Data Index: 249363 (C4 (Web Text))

Max Activating Token Index: 600