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

Dataset: The Pile

Neuron 2880 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1678714 (The Pile)

Max Activating Token Index: 749

Text #1

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1568744 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1403590 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3824. Min Act: -0.0000

Data Index: 523267 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.4522. Min Act: -0.0000

Data Index: 560407 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1185883 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1414148 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1460825 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1621912 (The Pile)

Max Activating Token Index: 232

Text #9

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1256939 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1118116 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1883709 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1089677 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1224681 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3573. Min Act: -0.0000

Data Index: 72187 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3428. Min Act: -0.0000

Data Index: 396320 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3640. Min Act: -0.0000

Data Index: 773069 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1327256 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1064545 (The Pile)

Max Activating Token Index: 167

Text #19

Max Range: 0.4522. Min Range: -0.4522

Max Act: 0.3588. Min Act: -0.0000

Data Index: 440946 (The Pile)

Max Activating Token Index: 348