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

Dataset: The Pile

Neuron 1764 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2325. Min Act: -0.0000

Data Index: 718557 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1299089 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1715644 (The Pile)

Max Activating Token Index: 283

Text #3

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1842. Min Act: -0.0000

Data Index: 124470 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1708485 (The Pile)

Max Activating Token Index: 627

Text #5

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1624020 (The Pile)

Max Activating Token Index: 970

Text #6

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1548. Min Act: -0.0000

Data Index: 703530 (The Pile)

Max Activating Token Index: 705

Text #7

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1470. Min Act: -0.0000

Data Index: 500539 (The Pile)

Max Activating Token Index: 395

Text #8

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1481. Min Act: -0.0000

Data Index: 519625 (The Pile)

Max Activating Token Index: 152

Text #9

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1700703 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1960401 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1198. Min Act: -0.0000

Data Index: 928949 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1342975 (The Pile)

Max Activating Token Index: 249

Text #13

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1082513 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1212. Min Act: -0.0000

Data Index: 678730 (The Pile)

Max Activating Token Index: 581

Text #15

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1791135 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1154. Min Act: -0.0000

Data Index: 549294 (The Pile)

Max Activating Token Index: 822

Text #17

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1098. Min Act: -0.0000

Data Index: 296090 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1191. Min Act: -0.0000

Data Index: 207038 (The Pile)

Max Activating Token Index: 1013

Text #19

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1571042 (The Pile)

Max Activating Token Index: 38