Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 471 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0978. Min Act: -0.0002

Data Index: 13114 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0002

Data Index: 103400 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1142528 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0912. Min Act: -0.0002

Data Index: 482255 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1177100 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1247098 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0823. Min Act: -0.0002

Data Index: 148914 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1167282 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0867. Min Act: -0.0002

Data Index: 945262 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0847. Min Act: -0.0002

Data Index: 901579 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1300686 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0863. Min Act: -0.0002

Data Index: 418868 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1142511 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1161839 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0771. Min Act: -0.0002

Data Index: 941274 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0791. Min Act: -0.0002

Data Index: 383689 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0804. Min Act: -0.0002

Data Index: 790542 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1021717 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0846. Min Act: -0.0002

Data Index: 750203 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0821. Min Act: -0.0002

Data Index: 989352 (C4 (Web Text))

Max Activating Token Index: 787