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

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

Neuron 2753 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: 0.2389. Min Range: -0.2389

Max Act: 0.2389. Min Act: -0.0001

Data Index: 386955 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2287. Min Act: -0.0001

Data Index: 451432 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2294. Min Act: -0.0001

Data Index: 898254 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2277. Min Act: -0.0001

Data Index: 247777 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2204. Min Act: -0.0001

Data Index: 481639 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2126. Min Act: -0.0001

Data Index: 467466 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2066. Min Act: -0.0002

Data Index: 438130 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2017. Min Act: -0.0002

Data Index: 924764 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2106. Min Act: -0.0001

Data Index: 1233841 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1943. Min Act: -0.0002

Data Index: 1266700 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1980. Min Act: -0.0002

Data Index: 1279106 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1869. Min Act: -0.0002

Data Index: 1074390 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1958. Min Act: -0.0001

Data Index: 1344871 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1030130 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1868. Min Act: -0.0002

Data Index: 979560 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1883. Min Act: -0.0001

Data Index: 593616 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1770. Min Act: -0.0002

Data Index: 973198 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1860. Min Act: -0.0002

Data Index: 1198573 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1839. Min Act: -0.0002

Data Index: 1066108 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2177. Min Act: -0.0002

Data Index: 101522 (C4 (Web Text))

Max Activating Token Index: 512