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

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

Neuron 1969 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.5340. Min Act: -0.0000

Data Index: 863546 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.4896. Min Act: -0.0000

Data Index: 728735 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.2419. Min Act: -0.0000

Data Index: 1138291 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.1385. Min Act: -0.0000

Data Index: 425147 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1334609 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.1077. Min Act: -0.0000

Data Index: 912696 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1063994 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0837. Min Act: -0.0000

Data Index: 20175 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0158. Min Act: -0.0000

Data Index: 1352888 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1108122 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0582. Min Act: -0.0000

Data Index: 972258 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9611. Min Act: -0.0000

Data Index: 344792 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0439. Min Act: -0.0000

Data Index: 1181051 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0305. Min Act: -0.0000

Data Index: 513401 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0092. Min Act: -0.0000

Data Index: 19652 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0723. Min Act: -0.0000

Data Index: 533587 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9920. Min Act: -0.0000

Data Index: 365556 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9898. Min Act: -0.0000

Data Index: 107827 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9838. Min Act: -0.0000

Data Index: 499612 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1161910 (C4 (Web Text))

Max Activating Token Index: 587