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

Dataset: The Pile

Neuron 3782 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: 0.5660. Min Range: -0.5660

Max Act: 0.5660. Min Act: -0.0000

Data Index: 277031 (The Pile)

Max Activating Token Index: 194

Text #1

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1589798 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4448. Min Act: -0.0000

Data Index: 683591 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4200. Min Act: -0.0000

Data Index: 285327 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1857177 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1700881 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1996964 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3932. Min Act: -0.0000

Data Index: 621320 (The Pile)

Max Activating Token Index: 533

Text #8

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3946. Min Act: -0.0000

Data Index: 562932 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3901. Min Act: -0.0000

Data Index: 893202 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1533419 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4013. Min Act: -0.0000

Data Index: 463147 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1455043 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3828. Min Act: -0.0000

Data Index: 258589 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.4091. Min Act: -0.0000

Data Index: 95516 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3849. Min Act: -0.0000

Data Index: 507058 (The Pile)

Max Activating Token Index: 214

Text #16

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1639669 (The Pile)

Max Activating Token Index: 631

Text #17

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1262936 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3770. Min Act: -0.0000

Data Index: 967638 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 0.5660. Min Range: -0.5660

Max Act: 0.3775. Min Act: -0.0000

Data Index: 870580 (The Pile)

Max Activating Token Index: 649