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

Dataset: The Pile

Neuron 4131 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: 0.2852. Min Range: -0.2852

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1853486 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2667. Min Act: -0.0000

Data Index: 669478 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.2197. Min Act: -0.0000

Data Index: 1782456 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1589. Min Act: -0.0000

Data Index: 876269 (The Pile)

Max Activating Token Index: 567

Text #4

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1768. Min Act: -0.0000

Data Index: 706102 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1596873 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1411987 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1300450 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1834247 (The Pile)

Max Activating Token Index: 148

Text #9

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1592372 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1025236 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1307. Min Act: -0.0000

Data Index: 985930 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1617312 (The Pile)

Max Activating Token Index: 863

Text #13

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1315. Min Act: -0.0000

Data Index: 50419 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1458. Min Act: -0.0000

Data Index: 905563 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1617. Min Act: -0.0000

Data Index: 9567 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1536. Min Act: -0.0000

Data Index: 192595 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1379. Min Act: -0.0000

Data Index: 700930 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1765856 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 0.2852. Min Range: -0.2852

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1304653 (The Pile)

Max Activating Token Index: 83