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

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

Neuron 4682 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2546. Min Range: -1.2546

Max Act: 1.1923. Min Act: -0.0000

Data Index: 31287 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 1.2546. Min Range: -1.2546

Max Act: 1.2546. Min Act: 0.0000

Data Index: 658017 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 1.2546. Min Range: -1.2546

Max Act: 1.1164. Min Act: -0.0000

Data Index: 767234 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 1.2546. Min Range: -1.2546

Max Act: 1.1561. Min Act: -0.0000

Data Index: 861515 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.2546. Min Range: -1.2546

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1050857 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 1.2546. Min Range: -1.2546

Max Act: 1.1043. Min Act: -0.0000

Data Index: 94611 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 1.2546. Min Range: -1.2546

Max Act: 1.0999. Min Act: -0.0000

Data Index: 112775 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.9725. Min Act: -0.0000

Data Index: 542080 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 1.2546. Min Range: -1.2546

Max Act: 1.0505. Min Act: -0.0000

Data Index: 674806 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.9817. Min Act: 0.0000

Data Index: 330203 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.9821. Min Act: -0.0000

Data Index: 1339492 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.2546. Min Range: -1.2546

Max Act: 1.0019. Min Act: -0.0000

Data Index: 850281 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.9545. Min Act: -0.0000

Data Index: 172122 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.9253. Min Act: -0.0000

Data Index: 225560 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.9118. Min Act: -0.0000

Data Index: 444730 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.9087. Min Act: -0.0000

Data Index: 387244 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.8712. Min Act: -0.0000

Data Index: 427180 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.8727. Min Act: -0.0000

Data Index: 977494 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.8793. Min Act: -0.0000

Data Index: 899631 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 1.2546. Min Range: -1.2546

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1161252 (C4 (Web Text))

Max Activating Token Index: 545