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

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

Neuron 5450 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0422. Min Act: -0.0000

Data Index: 267851 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0468. Min Act: -0.0000

Data Index: 787848 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1191688 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0255. Min Act: -0.0000

Data Index: 273489 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0316. Min Act: -0.0000

Data Index: 420730 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0284. Min Act: -0.0000

Data Index: 16492 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0273. Min Act: -0.0000

Data Index: 850941 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0274. Min Act: -0.0000

Data Index: 507460 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0269. Min Act: -0.0000

Data Index: 1134259 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0304. Min Act: -0.0000

Data Index: 1247344 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0257. Min Act: -0.0000

Data Index: 1271741 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0255. Min Act: -0.0000

Data Index: 775929 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0267. Min Act: -0.0000

Data Index: 1103005 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0261. Min Act: -0.0000

Data Index: 470664 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0305. Min Act: -0.0000

Data Index: 453830 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0238. Min Act: -0.0000

Data Index: 814810 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0246. Min Act: -0.0000

Data Index: 223872 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1054208 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0225. Min Act: -0.0000

Data Index: 1182824 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0264. Min Act: -0.0000

Data Index: 951453 (C4 (Web Text))

Max Activating Token Index: 803