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

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

Neuron 3756 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1243515 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1241673 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4930. Min Act: -0.0000

Data Index: 82217 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1072118 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4711. Min Act: -0.0000

Data Index: 754942 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4534. Min Act: -0.0000

Data Index: 565143 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1158211 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4756. Min Act: -0.0000

Data Index: 103357 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4434. Min Act: -0.0000

Data Index: 302516 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4391. Min Act: -0.0000

Data Index: 446210 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4476. Min Act: -0.0000

Data Index: 397971 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1214568 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1328754 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4554. Min Act: -0.0000

Data Index: 945792 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4570. Min Act: -0.0000

Data Index: 253134 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4353. Min Act: -0.0000

Data Index: 576816 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4206. Min Act: -0.0000

Data Index: 546556 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1069895 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4356. Min Act: -0.0000

Data Index: 189854 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.5817. Min Range: -0.5817

Max Act: 0.4429. Min Act: -0.0000

Data Index: 243404 (C4 (Web Text))

Max Activating Token Index: 804