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

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

Neuron 2691 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: 0.1802. Min Range: -0.1802

Max Act: 0.1802. Min Act: -0.0001

Data Index: 932247 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1424. Min Act: -0.0001

Data Index: 46354 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1113775 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1298623 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1390. Min Act: -0.0000

Data Index: 573839 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1395258 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1258064 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1202. Min Act: -0.0001

Data Index: 644840 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1353. Min Act: -0.0000

Data Index: 317050 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1159847 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1310325 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1246. Min Act: -0.0001

Data Index: 619968 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1060. Min Act: -0.0001

Data Index: 759796 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1147084 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1257035 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1204. Min Act: -0.0000

Data Index: 684508 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1216. Min Act: -0.0000

Data Index: 140520 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1221. Min Act: -0.0001

Data Index: 632617 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1431209 (Python Code)

Max Activating Token Index: 815

Text #19

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1010483 (C4 (Web Text))

Max Activating Token Index: 784