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

Dataset: The Pile

Neuron 2199 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: 0.9543. Min Range: -0.9543

Max Act: 0.9543. Min Act: 0.0000

Data Index: 1861482 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8965. Min Act: -0.0000

Data Index: 594523 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1043446 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8507. Min Act: 0.0000

Data Index: 176421 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1714027 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7860. Min Act: 0.0000

Data Index: 1327725 (The Pile)

Max Activating Token Index: 175

Text #6

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1831400 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.8083. Min Act: -0.0000

Data Index: 827642 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7924. Min Act: 0.0000

Data Index: 109574 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7903. Min Act: 0.0000

Data Index: 857520 (The Pile)

Max Activating Token Index: 82

Text #10

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7686. Min Act: -0.0000

Data Index: 570308 (The Pile)

Max Activating Token Index: 1014

Text #11

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7294. Min Act: -0.0000

Data Index: 221442 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7788. Min Act: 0.0000

Data Index: 1315458 (The Pile)

Max Activating Token Index: 694

Text #13

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7638. Min Act: -0.0000

Data Index: 968867 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7804. Min Act: -0.0000

Data Index: 245075 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1991020 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1450524 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7299. Min Act: -0.0000

Data Index: 389647 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7336. Min Act: -0.0000

Data Index: 862364 (The Pile)

Max Activating Token Index: 822

Text #19

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1171711 (The Pile)

Max Activating Token Index: 300