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

Dataset: The Pile

Neuron 3099 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: 5.5675. Min Range: -5.5675

Max Act: 5.5675. Min Act: -0.0000

Data Index: 1115083 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 5.5675. Min Range: -5.5675

Max Act: 5.1778. Min Act: -0.0000

Data Index: 1278491 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 5.5675. Min Range: -5.5675

Max Act: 5.0243. Min Act: -0.0000

Data Index: 1167989 (The Pile)

Max Activating Token Index: 331

Text #3

Max Range: 5.5675. Min Range: -5.5675

Max Act: 5.1389. Min Act: -0.0000

Data Index: 1353596 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 5.5675. Min Range: -5.5675

Max Act: 5.0630. Min Act: -0.0000

Data Index: 1469803 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 5.5675. Min Range: -5.5675

Max Act: 5.0312. Min Act: -0.0000

Data Index: 717581 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.9975. Min Act: -0.0000

Data Index: 270236 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.9797. Min Act: -0.0000

Data Index: 225838 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.9666. Min Act: -0.0000

Data Index: 230259 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.8564. Min Act: -0.0000

Data Index: 1391821 (The Pile)

Max Activating Token Index: 501

Text #10

Max Range: 5.5675. Min Range: -5.5675

Max Act: 5.0331. Min Act: -0.0000

Data Index: 1420043 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.9917. Min Act: -0.0000

Data Index: 1173326 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.5500. Min Act: -0.0000

Data Index: 1969521 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.9102. Min Act: -0.0000

Data Index: 78176 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.5480. Min Act: -0.0000

Data Index: 65913 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.4535. Min Act: -0.0000

Data Index: 463783 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.5614. Min Act: -0.0000

Data Index: 136231 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.6884. Min Act: -0.0000

Data Index: 842647 (The Pile)

Max Activating Token Index: 931

Text #18

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.5357. Min Act: -0.0000

Data Index: 757573 (The Pile)

Max Activating Token Index: 335

Text #19

Max Range: 5.5675. Min Range: -5.5675

Max Act: 4.5246. Min Act: -0.0000

Data Index: 1347784 (The Pile)

Max Activating Token Index: 414