Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2583 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1463. Min Act: -0.0002

Data Index: 1169295 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1516. Min Act: -0.0002

Data Index: 788251 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1526. Min Act: -0.0002

Data Index: 637221 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1376. Min Act: -0.0002

Data Index: 881550 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1385. Min Act: -0.0002

Data Index: 161684 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1348. Min Act: -0.0002

Data Index: 1258368 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1310. Min Act: -0.0002

Data Index: 677536 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1335. Min Act: -0.0002

Data Index: 1249710 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1323. Min Act: -0.0002

Data Index: 303855 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1353. Min Act: -0.0002

Data Index: 434451 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1349. Min Act: -0.0002

Data Index: 908691 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1289. Min Act: -0.0002

Data Index: 1045110 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1296. Min Act: -0.0002

Data Index: 864807 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1247. Min Act: -0.0002

Data Index: 1309620 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1241. Min Act: -0.0002

Data Index: 22400 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1106. Min Act: -0.0002

Data Index: 371154 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1223. Min Act: -0.0002

Data Index: 6290 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1227. Min Act: -0.0002

Data Index: 279938 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1177. Min Act: -0.0002

Data Index: 557434 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1119. Min Act: -0.0002

Data Index: 730667 (C4 (Web Text))

Max Activating Token Index: 157