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

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

Neuron 156 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0001

Data Index: 695746 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1492489 (Python Code)

Max Activating Token Index: 931

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0326. Min Act: -0.0001

Data Index: 309741 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0311. Min Act: -0.0001

Data Index: 281279 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1543702 (Python Code)

Max Activating Token Index: 267

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1617244 (Python Code)

Max Activating Token Index: 563

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0269. Min Act: -0.0001

Data Index: 51332 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1491841 (Python Code)

Max Activating Token Index: 580

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0254. Min Act: -0.0001

Data Index: 994945 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0262. Min Act: -0.0001

Data Index: 911744 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1541813 (Python Code)

Max Activating Token Index: 852

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0252. Min Act: -0.0001

Data Index: 225636 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0243. Min Act: -0.0001

Data Index: 142356 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0246. Min Act: -0.0001

Data Index: 79969 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1600807 (Python Code)

Max Activating Token Index: 859

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1647065 (Python Code)

Max Activating Token Index: 751

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1402720 (Python Code)

Max Activating Token Index: 748

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0251. Min Act: -0.0001

Data Index: 442752 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1461789 (Python Code)

Max Activating Token Index: 558

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1641672 (Python Code)

Max Activating Token Index: 330