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

Dataset: The Pile

Neuron 627 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1586086 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1587. Min Act: -0.0000

Data Index: 217502 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1518. Min Act: -0.0000

Data Index: 450152 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1086215 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1504. Min Act: -0.0000

Data Index: 505544 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1469. Min Act: -0.0000

Data Index: 1888848 (The Pile)

Max Activating Token Index: 902

Text #6

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1913269 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1466. Min Act: -0.0000

Data Index: 902428 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1464248 (The Pile)

Max Activating Token Index: 348

Text #9

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1937638 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1176861 (The Pile)

Max Activating Token Index: 807

Text #11

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1318. Min Act: -0.0000

Data Index: 235940 (The Pile)

Max Activating Token Index: 755

Text #12

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1154818 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1339. Min Act: -0.0000

Data Index: 382652 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1817194 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1947937 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1753804 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1273. Min Act: -0.0000

Data Index: 590488 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1195. Min Act: -0.0000

Data Index: 340404 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1969696 (The Pile)

Max Activating Token Index: 436