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

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

Neuron 3008 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: 1.1263. Min Range: -1.1263

Max Act: 1.1263. Min Act: -0.0000

Data Index: 368460 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 1.1263. Min Range: -1.1263

Max Act: 1.0590. Min Act: 0.0001

Data Index: 597030 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.9451. Min Act: -0.0000

Data Index: 365691 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.9511. Min Act: -0.0000

Data Index: 300938 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8763. Min Act: -0.0000

Data Index: 217723 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8764. Min Act: -0.0000

Data Index: 276152 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8667. Min Act: -0.0000

Data Index: 849291 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8400. Min Act: -0.0000

Data Index: 786794 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8579. Min Act: -0.0000

Data Index: 640265 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8791. Min Act: -0.0000

Data Index: 153955 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8127. Min Act: -0.0000

Data Index: 140132 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8260. Min Act: -0.0000

Data Index: 26668 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8237. Min Act: -0.0000

Data Index: 311317 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7678. Min Act: -0.0000

Data Index: 207411 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7993. Min Act: -0.0000

Data Index: 659491 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1114475 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7675. Min Act: 0.0000

Data Index: 943766 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7591. Min Act: -0.0000

Data Index: 932547 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1163376 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 1.1263. Min Range: -1.1263

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1195691 (C4 (Web Text))

Max Activating Token Index: 742