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

Dataset: The Pile

Neuron 1709 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: 1.4632. Min Range: -1.4632

Max Act: 1.4632. Min Act: -0.0000

Data Index: 68507 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3578. Min Act: -0.0000

Data Index: 248609 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3726. Min Act: -0.0000

Data Index: 708608 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.4114. Min Act: -0.0000

Data Index: 963763 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3614. Min Act: -0.0000

Data Index: 665521 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3159. Min Act: -0.0000

Data Index: 173246 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2784. Min Act: -0.0000

Data Index: 788843 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2791. Min Act: -0.0000

Data Index: 222702 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3064. Min Act: -0.0000

Data Index: 171898 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2745. Min Act: -0.0000

Data Index: 1728952 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2426. Min Act: -0.0000

Data Index: 778664 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2782. Min Act: -0.0000

Data Index: 1529014 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2785. Min Act: -0.0000

Data Index: 1048687 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1934011 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2237. Min Act: -0.0000

Data Index: 818367 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1108799 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1910. Min Act: -0.0000

Data Index: 1145322 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1899401 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2699. Min Act: -0.0000

Data Index: 525899 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1531. Min Act: -0.0000

Data Index: 409684 (The Pile)

Max Activating Token Index: 895