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

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

Neuron 1272 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: 0.1979. Min Range: -0.1979

Max Act: 0.1753. Min Act: -0.0001

Data Index: 840361 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1028272 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1910. Min Act: -0.0001

Data Index: 743827 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1121655 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1925. Min Act: -0.0001

Data Index: 28572 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1896. Min Act: -0.0001

Data Index: 1232141 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1939. Min Act: -0.0001

Data Index: 706753 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1823. Min Act: -0.0001

Data Index: 1072858 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1755. Min Act: -0.0001

Data Index: 611883 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1796. Min Act: -0.0001

Data Index: 266052 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1105776 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1745. Min Act: -0.0001

Data Index: 332649 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1683. Min Act: -0.0001

Data Index: 954173 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1726. Min Act: -0.0001

Data Index: 950790 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1477. Min Act: -0.0001

Data Index: 279115 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1738. Min Act: -0.0001

Data Index: 259245 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1662. Min Act: -0.0001

Data Index: 52261 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1665. Min Act: -0.0001

Data Index: 402984 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1665. Min Act: -0.0001

Data Index: 468808 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1645. Min Act: -0.0001

Data Index: 476027 (C4 (Web Text))

Max Activating Token Index: 544