Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 40 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.5627. Min Act: -0.0000

Data Index: 513834 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.9003. Min Act: -0.0000

Data Index: 165890 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.1798. Min Act: -0.0000

Data Index: 1154971 (The Pile)

Max Activating Token Index: 671

Text #3

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.1556. Min Act: -0.0000

Data Index: 952610 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.9930. Min Act: -0.0000

Data Index: 1067992 (The Pile)

Max Activating Token Index: 584

Text #5

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.7772. Min Act: -0.0000

Data Index: 157445 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.0103. Min Act: -0.0000

Data Index: 496219 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.7503. Min Act: -0.0000

Data Index: 1822419 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.9916. Min Act: -0.0000

Data Index: 1885867 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 3.5627. Min Range: -3.5627

Max Act: 3.0571. Min Act: -0.0000

Data Index: 633217 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.9059. Min Act: -0.0000

Data Index: 173846 (The Pile)

Max Activating Token Index: 360

Text #11

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.5695. Min Act: -0.0000

Data Index: 1895604 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.8321. Min Act: -0.0000

Data Index: 611817 (The Pile)

Max Activating Token Index: 895

Text #13

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.6969. Min Act: -0.0000

Data Index: 1698483 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.6681. Min Act: -0.0000

Data Index: 1254265 (The Pile)

Max Activating Token Index: 637

Text #15

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.7080. Min Act: -0.0000

Data Index: 1662355 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.7159. Min Act: -0.0000

Data Index: 530364 (The Pile)

Max Activating Token Index: 749

Text #17

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.6658. Min Act: -0.0000

Data Index: 1978330 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.4903. Min Act: -0.0000

Data Index: 823431 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 3.5627. Min Range: -3.5627

Max Act: 2.4939. Min Act: -0.0000

Data Index: 1611043 (The Pile)

Max Activating Token Index: 366