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

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

Neuron 4188 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0465. Min Act: -0.0001

Data Index: 497000 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0367. Min Act: -0.0001

Data Index: 763083 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0347. Min Act: -0.0001

Data Index: 370946 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0364. Min Act: -0.0001

Data Index: 305285 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1017817 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0332. Min Act: -0.0001

Data Index: 964254 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0329. Min Act: -0.0001

Data Index: 332357 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1356616 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0305. Min Act: -0.0001

Data Index: 397771 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0313. Min Act: -0.0001

Data Index: 530106 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1249589 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0335. Min Act: -0.0001

Data Index: 975971 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0303. Min Act: -0.0001

Data Index: 117306 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0291. Min Act: -0.0001

Data Index: 790076 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1349604 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0258. Min Act: -0.0001

Data Index: 997377 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0251. Min Act: -0.0001

Data Index: 224989 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0230. Min Act: -0.0001

Data Index: 187954 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1341040 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0231. Min Act: -0.0001

Data Index: 313022 (C4 (Web Text))

Max Activating Token Index: 853