Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 891 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1023090 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1188969 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1435. Min Act: -0.0001

Data Index: 286751 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1362. Min Act: -0.0000

Data Index: 679537 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1333. Min Act: -0.0000

Data Index: 959221 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1245. Min Act: -0.0001

Data Index: 917211 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1239. Min Act: -0.0001

Data Index: 208095 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1270. Min Act: -0.0000

Data Index: 808513 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1295. Min Act: -0.0000

Data Index: 998472 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1259. Min Act: -0.0001

Data Index: 532947 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1223. Min Act: -0.0000

Data Index: 866320 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1144899 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1285. Min Act: -0.0000

Data Index: 606911 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1274. Min Act: -0.0000

Data Index: 86057 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1240. Min Act: -0.0000

Data Index: 548149 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1287. Min Act: -0.0001

Data Index: 837237 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1224554 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1157. Min Act: -0.0001

Data Index: 371117 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1322244 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1307504 (C4 (Web Text))

Max Activating Token Index: 83