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

Dataset: The Pile

Neuron 1217 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1519558 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1514. Min Act: -0.0001

Data Index: 1942703 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1917522 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1522. Min Act: -0.0001

Data Index: 544211 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1511. Min Act: -0.0000

Data Index: 194173 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1816064 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1572717 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1874162 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1318. Min Act: -0.0000

Data Index: 53786 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1277. Min Act: -0.0000

Data Index: 353708 (The Pile)

Max Activating Token Index: 189

Text #10

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1301. Min Act: -0.0000

Data Index: 1025551 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1249. Min Act: -0.0000

Data Index: 510468 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1417986 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1240. Min Act: -0.0000

Data Index: 76811 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1310. Min Act: -0.0000

Data Index: 633202 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1369967 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1310. Min Act: -0.0000

Data Index: 571138 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1262. Min Act: -0.0001

Data Index: 518586 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1093675 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1396723 (The Pile)

Max Activating Token Index: 502