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

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

Neuron 4228 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1109477 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1242776 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1076545 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1336. Min Act: -0.0000

Data Index: 43038 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1265. Min Act: -0.0000

Data Index: 358980 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1410. Min Act: -0.0000

Data Index: 230704 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1287. Min Act: -0.0000

Data Index: 375317 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1299. Min Act: -0.0000

Data Index: 209964 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1250. Min Act: -0.0000

Data Index: 206554 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1247. Min Act: -0.0000

Data Index: 55098 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1198. Min Act: -0.0000

Data Index: 10869 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1211. Min Act: -0.0000

Data Index: 241419 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1310846 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1000813 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1248. Min Act: -0.0000

Data Index: 613688 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1143. Min Act: -0.0000

Data Index: 327012 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1154. Min Act: -0.0000

Data Index: 557811 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1140. Min Act: -0.0000

Data Index: 11566 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1092. Min Act: -0.0000

Data Index: 233249 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1124. Min Act: -0.0000

Data Index: 699036 (C4 (Web Text))

Max Activating Token Index: 272