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

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

Neuron 1928 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0562. Min Range: -1.0562

Max Act: 1.0562. Min Act: -0.0002

Data Index: 997768 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9141. Min Act: -0.0002

Data Index: 1318474 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9556. Min Act: -0.0002

Data Index: 1001859 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9520. Min Act: -0.0001

Data Index: 1318867 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.7643. Min Act: -0.0001

Data Index: 520220 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9238. Min Act: -0.0002

Data Index: 912737 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9079. Min Act: -0.0001

Data Index: 571223 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8016. Min Act: -0.0001

Data Index: 767791 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8720. Min Act: -0.0002

Data Index: 968568 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8269. Min Act: -0.0002

Data Index: 52448 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9036. Min Act: -0.0001

Data Index: 446524 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 1.0562. Min Range: -1.0562

Max Act: 1.0162. Min Act: -0.0002

Data Index: 1080367 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8475. Min Act: -0.0002

Data Index: 994103 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9082. Min Act: -0.0002

Data Index: 674172 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9107. Min Act: -0.0002

Data Index: 858821 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8125. Min Act: -0.0001

Data Index: 733920 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8479. Min Act: -0.0002

Data Index: 773668 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8234. Min Act: -0.0002

Data Index: 104889 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9158. Min Act: -0.0001

Data Index: 755844 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1319225 (C4 (Web Text))

Max Activating Token Index: 613