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

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

Neuron 3251 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1082324 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1175436 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1409. Min Act: -0.0001

Data Index: 565605 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1254576 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1066915 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1269. Min Act: -0.0001

Data Index: 84291 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1295062 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1342. Min Act: -0.0001

Data Index: 516096 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1293380 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1276913 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1269. Min Act: -0.0001

Data Index: 877039 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1142. Min Act: -0.0001

Data Index: 556438 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1177. Min Act: -0.0001

Data Index: 344474 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1137. Min Act: -0.0001

Data Index: 555024 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1115. Min Act: -0.0001

Data Index: 788018 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1223764 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1177910 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1159. Min Act: -0.0001

Data Index: 14240 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1138. Min Act: -0.0001

Data Index: 880623 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1126. Min Act: -0.0001

Data Index: 80571 (C4 (Web Text))

Max Activating Token Index: 159