Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 273 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1491. Min Act: -0.0001

Data Index: 688907 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1326. Min Act: -0.0001

Data Index: 639614 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1367. Min Act: -0.0001

Data Index: 443174 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1338. Min Act: -0.0001

Data Index: 525932 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1494. Min Act: -0.0001

Data Index: 880920 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1350. Min Act: -0.0001

Data Index: 496425 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1336. Min Act: -0.0001

Data Index: 287710 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1015896 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1371. Min Act: -0.0001

Data Index: 231364 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1241149 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1343. Min Act: -0.0001

Data Index: 244436 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1288. Min Act: -0.0001

Data Index: 2712 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1295. Min Act: -0.0001

Data Index: 314334 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1305. Min Act: -0.0001

Data Index: 58421 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1317445 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1269. Min Act: -0.0001

Data Index: 403385 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1198. Min Act: -0.0001

Data Index: 139037 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1316. Min Act: -0.0001

Data Index: 607578 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1176. Min Act: -0.0001

Data Index: 885297 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1324662 (C4 (Web Text))

Max Activating Token Index: 109