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

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

Neuron 3434 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: 0.9883. Min Range: -0.9883

Max Act: 0.9883. Min Act: -0.0000

Data Index: 45614 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8020. Min Act: -0.0000

Data Index: 893336 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8677. Min Act: -0.0000

Data Index: 408519 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7592. Min Act: -0.0000

Data Index: 515879 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8123. Min Act: -0.0000

Data Index: 675858 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7967. Min Act: -0.0000

Data Index: 704601 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6728. Min Act: -0.0000

Data Index: 712861 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1119139 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7832. Min Act: -0.0000

Data Index: 678552 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1302281 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7450. Min Act: -0.0000

Data Index: 911513 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7897. Min Act: -0.0000

Data Index: 420708 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7397. Min Act: -0.0000

Data Index: 673361 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7421. Min Act: -0.0000

Data Index: 832330 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7099. Min Act: -0.0000

Data Index: 165234 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6592. Min Act: -0.0000

Data Index: 499239 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7432. Min Act: -0.0000

Data Index: 420472 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.6956. Min Act: -0.0000

Data Index: 421015 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1336584 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.9883. Min Range: -0.9883

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1150187 (C4 (Web Text))

Max Activating Token Index: 895