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

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

Neuron 3494 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0537. Min Range: -4.0537

Max Act: 4.0537. Min Act: -0.0000

Data Index: 691099 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 4.0537. Min Range: -4.0537

Max Act: 4.0123. Min Act: -0.0000

Data Index: 249437 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.6699. Min Act: -0.0000

Data Index: 229618 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.5100. Min Act: -0.0000

Data Index: 956483 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.5920. Min Act: -0.0000

Data Index: 1001666 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.7242. Min Act: -0.0000

Data Index: 447178 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.2783. Min Act: -0.0000

Data Index: 814844 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.3986. Min Act: -0.0000

Data Index: 639463 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.2215. Min Act: -0.0000

Data Index: 1299262 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.0674. Min Act: -0.0001

Data Index: 1319491 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.3750. Min Act: -0.0000

Data Index: 846816 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.9315. Min Act: -0.0000

Data Index: 1325056 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.3094. Min Act: -0.0001

Data Index: 711733 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.1193. Min Act: -0.0000

Data Index: 1020648 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 4.0537. Min Range: -4.0537

Max Act: 2.9503. Min Act: -0.0000

Data Index: 1167704 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.0175. Min Act: -0.0000

Data Index: 915235 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.1439. Min Act: -0.0001

Data Index: 79307 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.0016. Min Act: -0.0000

Data Index: 590252 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.1196. Min Act: -0.0001

Data Index: 1009659 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 4.0537. Min Range: -4.0537

Max Act: 3.1026. Min Act: -0.0000

Data Index: 1020695 (C4 (Web Text))

Max Activating Token Index: 488