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

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

Neuron 2153 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: 0.9790. Min Range: -0.9790

Max Act: 0.9790. Min Act: -0.0002

Data Index: 55395 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.9723. Min Act: -0.0002

Data Index: 218732 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.9269. Min Act: -0.0001

Data Index: 1646928 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8799. Min Act: -0.0001

Data Index: 1512019 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.9068. Min Act: -0.0001

Data Index: 1249150 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8851. Min Act: -0.0001

Data Index: 172462 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8644. Min Act: -0.0001

Data Index: 1363880 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8726. Min Act: -0.0001

Data Index: 21835 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8105. Min Act: -0.0002

Data Index: 1309129 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8217. Min Act: -0.0002

Data Index: 824560 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8621. Min Act: -0.0001

Data Index: 1535930 (Python Code)

Max Activating Token Index: 447

Text #11

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8391. Min Act: -0.0001

Data Index: 1470522 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8074. Min Act: -0.0001

Data Index: 1555721 (Python Code)

Max Activating Token Index: 984

Text #13

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8040. Min Act: -0.0001

Data Index: 1434872 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8228. Min Act: -0.0001

Data Index: 263366 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7956. Min Act: -0.0001

Data Index: 1445085 (Python Code)

Max Activating Token Index: 493

Text #16

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7932. Min Act: -0.0001

Data Index: 796366 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8392. Min Act: -0.0001

Data Index: 613699 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.7694. Min Act: -0.0001

Data Index: 407531 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.9790. Min Range: -0.9790

Max Act: 0.8117. Min Act: -0.0002

Data Index: 4815 (C4 (Web Text))

Max Activating Token Index: 527