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

Dataset: The Pile

Neuron 1057 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: 1.4350. Min Range: -1.4350

Max Act: 1.4350. Min Act: -0.0000

Data Index: 558744 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1115091 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.3257. Min Act: -0.0000

Data Index: 1462027 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.3497. Min Act: -0.0000

Data Index: 1910550 (The Pile)

Max Activating Token Index: 116

Text #4

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1784167 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1144079 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1111412 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.1398. Min Act: -0.0000

Data Index: 997076 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.1139. Min Act: -0.0000

Data Index: 899841 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.1799. Min Act: -0.0000

Data Index: 862705 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.0486. Min Act: -0.0000

Data Index: 1551233 (The Pile)

Max Activating Token Index: 804

Text #11

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1354358 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1147715 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1319254 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.0334. Min Act: -0.0000

Data Index: 123708 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1235332 (The Pile)

Max Activating Token Index: 812

Text #16

Max Range: 1.4350. Min Range: -1.4350

Max Act: 0.9540. Min Act: -0.0000

Data Index: 592338 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.0322. Min Act: -0.0000

Data Index: 638610 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.0420. Min Act: -0.0000

Data Index: 1783301 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 1.4350. Min Range: -1.4350

Max Act: 1.0197. Min Act: -0.0000

Data Index: 463275 (The Pile)

Max Activating Token Index: 288