Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2476 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1168612 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7901. Min Act: -0.0000

Data Index: 563641 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.8282. Min Act: -0.0000

Data Index: 294556 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7445. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6670. Min Act: -0.0000

Data Index: 538457 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6702. Min Act: -0.0000

Data Index: 434720 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6799. Min Act: -0.0000

Data Index: 888239 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6177. Min Act: -0.0000

Data Index: 608193 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5941. Min Act: -0.0000

Data Index: 715764 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6237. Min Act: -0.0000

Data Index: 551258 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6818. Min Act: -0.0000

Data Index: 740468 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6006. Min Act: -0.0000

Data Index: 698171 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5922. Min Act: -0.0000

Data Index: 67909 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5537. Min Act: -0.0000

Data Index: 244417 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1273754 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5283. Min Act: -0.0000

Data Index: 691822 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5594. Min Act: 0.0000

Data Index: 40002 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5112. Min Act: -0.0000

Data Index: 240946 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.5598. Min Act: -0.0000

Data Index: 910062 (C4 (Web Text))

Max Activating Token Index: 378