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

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

Neuron 2147 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1945. Min Act: -0.0004

Data Index: 496212 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1937. Min Act: -0.0004

Data Index: 27054 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1776. Min Act: -0.0004

Data Index: 35178 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1970. Min Act: -0.0004

Data Index: 163383 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1923. Min Act: -0.0004

Data Index: 1092190 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.2104. Min Act: -0.0004

Data Index: 930715 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1850. Min Act: -0.0004

Data Index: 974802 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1898. Min Act: -0.0004

Data Index: 221764 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1690. Min Act: -0.0004

Data Index: 1044085 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1860. Min Act: -0.0004

Data Index: 209891 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1671. Min Act: -0.0004

Data Index: 714542 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1740. Min Act: -0.0004

Data Index: 430654 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1768. Min Act: -0.0004

Data Index: 722473 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1780. Min Act: -0.0004

Data Index: 71026 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1784. Min Act: -0.0004

Data Index: 1121053 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1640. Min Act: -0.0004

Data Index: 468387 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1535. Min Act: -0.0004

Data Index: 1057256 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1432. Min Act: -0.0004

Data Index: 346560 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1330. Min Act: -0.0004

Data Index: 943513 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1804. Min Act: -0.0004

Data Index: 797647 (C4 (Web Text))

Max Activating Token Index: 885