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

Dataset: The Pile

Neuron 4447 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: 5.3646. Min Range: -5.3646

Max Act: 5.3646. Min Act: -0.0000

Data Index: 1370122 (The Pile)

Max Activating Token Index: 407

Text #1

Max Range: 5.3646. Min Range: -5.3646

Max Act: 5.0946. Min Act: -0.0000

Data Index: 19103 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.5538. Min Act: -0.0000

Data Index: 728151 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.8811. Min Act: -0.0000

Data Index: 860239 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.9053. Min Act: -0.0000

Data Index: 1437771 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.8396. Min Act: -0.0000

Data Index: 1010262 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.0542. Min Act: -0.0000

Data Index: 1850712 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 5.3646. Min Range: -5.3646

Max Act: 3.9805. Min Act: -0.0000

Data Index: 1779508 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 5.3646. Min Range: -5.3646

Max Act: 3.8638. Min Act: -0.0000

Data Index: 914044 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.1814. Min Act: -0.0000

Data Index: 1921969 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.3160. Min Act: -0.0000

Data Index: 782906 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.1003. Min Act: -0.0000

Data Index: 1556876 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.1378. Min Act: -0.0000

Data Index: 1417911 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 5.3646. Min Range: -5.3646

Max Act: 3.9046. Min Act: -0.0000

Data Index: 377885 (The Pile)

Max Activating Token Index: 437

Text #14

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.2093. Min Act: -0.0000

Data Index: 248003 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 5.3646. Min Range: -5.3646

Max Act: 4.1686. Min Act: -0.0000

Data Index: 213837 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 5.3646. Min Range: -5.3646

Max Act: 3.8581. Min Act: -0.0000

Data Index: 552478 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 5.3646. Min Range: -5.3646

Max Act: 3.9690. Min Act: -0.0000

Data Index: 1017205 (The Pile)

Max Activating Token Index: 389

Text #18

Max Range: 5.3646. Min Range: -5.3646

Max Act: 3.8750. Min Act: -0.0000

Data Index: 1597763 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 5.3646. Min Range: -5.3646

Max Act: 3.9468. Min Act: -0.0000

Data Index: 1220748 (The Pile)

Max Activating Token Index: 335