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

Dataset: The Pile

Neuron 4469 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.2158. Min Act: -0.0000

Data Index: 444194 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1966244 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1456. Min Act: -0.0000

Data Index: 448026 (The Pile)

Max Activating Token Index: 711

Text #3

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1387. Min Act: -0.0000

Data Index: 500115 (The Pile)

Max Activating Token Index: 170

Text #4

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1582. Min Act: -0.0000

Data Index: 756740 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1503. Min Act: -0.0000

Data Index: 768984 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1076708 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1943282 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1398. Min Act: -0.0000

Data Index: 660200 (The Pile)

Max Activating Token Index: 241

Text #9

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1170111 (The Pile)

Max Activating Token Index: 782

Text #10

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1815639 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1294. Min Act: -0.0000

Data Index: 794795 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1683568 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1112427 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1186677 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1122798 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1300664 (The Pile)

Max Activating Token Index: 840

Text #17

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1191512 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1250280 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.2158. Min Range: -0.2158

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1237585 (The Pile)

Max Activating Token Index: 931