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

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

Neuron 2957 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0592. Min Act: -0.0003

Data Index: 465147 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1056892 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0609. Min Act: -0.0003

Data Index: 505833 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0605. Min Act: -0.0003

Data Index: 519280 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0605. Min Act: -0.0003

Data Index: 777367 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1077904 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0601. Min Act: -0.0003

Data Index: 975614 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0625. Min Act: -0.0003

Data Index: 631164 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0577. Min Act: -0.0003

Data Index: 242786 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0599. Min Act: -0.0003

Data Index: 508495 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0599. Min Act: -0.0003

Data Index: 996090 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1218669 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0569. Min Act: -0.0003

Data Index: 256222 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0588. Min Act: -0.0003

Data Index: 767641 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1332150 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0564. Min Act: -0.0003

Data Index: 834285 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0533. Min Act: -0.0003

Data Index: 889956 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0582. Min Act: -0.0003

Data Index: 590465 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0561. Min Act: -0.0003

Data Index: 803296 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1037339 (C4 (Web Text))

Max Activating Token Index: 46