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

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

Neuron 3094 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1291661 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1045637 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1354542 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0376. Min Act: -0.0002

Data Index: 516279 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0321. Min Act: -0.0002

Data Index: 324493 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1228437 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1592606 (Python Code)

Max Activating Token Index: 351

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0328. Min Act: -0.0002

Data Index: 850130 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1460975 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1063874 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1395622 (Python Code)

Max Activating Token Index: 175

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1244280 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0345. Min Act: -0.0002

Data Index: 839920 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0347. Min Act: -0.0002

Data Index: 492602 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0332. Min Act: -0.0002

Data Index: 564924 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1122057 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0348. Min Act: -0.0002

Data Index: 651111 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0324. Min Act: -0.0002

Data Index: 541188 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1342614 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1343560 (C4 (Web Text))

Max Activating Token Index: 562