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

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

Neuron 3524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.6473. Min Act: -0.0000

Data Index: 129010 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1156502 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5346. Min Act: -0.0001

Data Index: 993478 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5344. Min Act: -0.0000

Data Index: 664465 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5118. Min Act: -0.0000

Data Index: 775569 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.5198. Min Act: -0.0001

Data Index: 1196708 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4948. Min Act: -0.0001

Data Index: 864994 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4739. Min Act: -0.0001

Data Index: 985919 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4754. Min Act: -0.0001

Data Index: 863521 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4774. Min Act: -0.0000

Data Index: 477306 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4660. Min Act: -0.0001

Data Index: 1189337 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1290075 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4793. Min Act: -0.0001

Data Index: 503171 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4788. Min Act: -0.0000

Data Index: 146759 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4630. Min Act: -0.0000

Data Index: 646331 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4489. Min Act: -0.0000

Data Index: 323983 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1013670 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4425. Min Act: -0.0000

Data Index: 220616 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4445. Min Act: -0.0000

Data Index: 16495 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.6473. Min Range: -0.6473

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1353255 (C4 (Web Text))

Max Activating Token Index: 868