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

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

Neuron 2262 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1597. Min Act: -0.0000

Data Index: 878927 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1544. Min Act: -0.0000

Data Index: 33097 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1439. Min Act: -0.0000

Data Index: 105726 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1272320 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1339. Min Act: -0.0000

Data Index: 67014 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1268. Min Act: -0.0000

Data Index: 550704 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1295. Min Act: -0.0000

Data Index: 204847 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1239. Min Act: -0.0000

Data Index: 1141812 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1273. Min Act: -0.0000

Data Index: 303464 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1175076 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1105927 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1124. Min Act: -0.0000

Data Index: 546090 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1294. Min Act: -0.0000

Data Index: 771224 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1161. Min Act: -0.0000

Data Index: 392530 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1014412 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1204. Min Act: -0.0000

Data Index: 709990 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1181. Min Act: -0.0000

Data Index: 536647 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1162. Min Act: -0.0000

Data Index: 257640 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1094. Min Act: -0.0000

Data Index: 586040 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1302094 (C4 (Web Text))

Max Activating Token Index: 730