Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 729 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7503. Min Act: -0.0001

Data Index: 723249 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7820. Min Act: -0.0001

Data Index: 442889 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7232. Min Act: -0.0001

Data Index: 660733 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6682. Min Act: -0.0001

Data Index: 698366 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6851. Min Act: -0.0001

Data Index: 141489 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6536. Min Act: -0.0001

Data Index: 998510 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6627. Min Act: -0.0001

Data Index: 1010639 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1021540 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6463. Min Act: -0.0001

Data Index: 32995 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6191. Min Act: -0.0001

Data Index: 1077539 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6209. Min Act: -0.0001

Data Index: 510485 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5969. Min Act: -0.0001

Data Index: 157202 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6006. Min Act: -0.0001

Data Index: 241030 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6461. Min Act: -0.0001

Data Index: 311640 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6217. Min Act: -0.0001

Data Index: 704814 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6153. Min Act: -0.0001

Data Index: 409022 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6259. Min Act: -0.0001

Data Index: 703229 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5808. Min Act: -0.0001

Data Index: 431975 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5807. Min Act: -0.0001

Data Index: 466553 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5624. Min Act: -0.0001

Data Index: 890124 (C4 (Web Text))

Max Activating Token Index: 861