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

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

Neuron 3219 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1677. Min Act: -0.0001

Data Index: 712613 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1464. Min Act: -0.0001

Data Index: 479304 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1405. Min Act: -0.0001

Data Index: 1414644 (Python Code)

Max Activating Token Index: 833

Text #3

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1389. Min Act: -0.0001

Data Index: 790903 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1342. Min Act: -0.0001

Data Index: 561135 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1389107 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1387777 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1395979 (Python Code)

Max Activating Token Index: 616

Text #8

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1351. Min Act: -0.0001

Data Index: 820452 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1387. Min Act: -0.0001

Data Index: 747551 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1292. Min Act: -0.0001

Data Index: 1390651 (Python Code)

Max Activating Token Index: 976

Text #11

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1446136 (Python Code)

Max Activating Token Index: 126

Text #12

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1512576 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1297. Min Act: -0.0001

Data Index: 333352 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1203. Min Act: -0.0001

Data Index: 1108397 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1450511 (Python Code)

Max Activating Token Index: 297

Text #16

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1238. Min Act: -0.0001

Data Index: 289366 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1185. Min Act: -0.0001

Data Index: 645082 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1279. Min Act: -0.0001

Data Index: 44769 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1275. Min Act: -0.0001

Data Index: 923589 (C4 (Web Text))

Max Activating Token Index: 40