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

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

Neuron 2893 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2480. Min Act: -0.0000

Data Index: 652648 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2258. Min Act: -0.0000

Data Index: 760428 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1285838 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2053. Min Act: -0.0001

Data Index: 732510 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2039. Min Act: -0.0001

Data Index: 586726 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2052. Min Act: 0.0002

Data Index: 509820 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1276960 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1979. Min Act: -0.0001

Data Index: 988964 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1014195 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1936. Min Act: -0.0001

Data Index: 857579 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1915. Min Act: -0.0001

Data Index: 400082 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1844. Min Act: -0.0000

Data Index: 818258 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1901. Min Act: 0.0000

Data Index: 1329522 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1073363 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1898. Min Act: 0.0000

Data Index: 899729 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1198440 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1896. Min Act: -0.0000

Data Index: 633196 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1905. Min Act: -0.0000

Data Index: 793138 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1020228 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.2480. Min Range: -0.2480

Max Act: 0.1869. Min Act: -0.0000

Data Index: 797652 (C4 (Web Text))

Max Activating Token Index: 105