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

Dataset: The Pile

Neuron 2146 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: 0.3957. Min Range: -0.3957

Max Act: 0.3957. Min Act: -0.0000

Data Index: 435650 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1727326 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3587. Min Act: -0.0000

Data Index: 294655 (The Pile)

Max Activating Token Index: 268

Text #3

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3282. Min Act: -0.0000

Data Index: 889311 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1572820 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2800. Min Act: -0.0000

Data Index: 38084 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3088. Min Act: -0.0000

Data Index: 368099 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3258. Min Act: 0.0001

Data Index: 150015 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1901532 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3148. Min Act: -0.0000

Data Index: 466790 (The Pile)

Max Activating Token Index: 800

Text #10

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1753610 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3069. Min Act: -0.0000

Data Index: 34301 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1950494 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1364772 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1902821 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3048. Min Act: -0.0000

Data Index: 321672 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2969. Min Act: -0.0000

Data Index: 647474 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3054. Min Act: -0.0000

Data Index: 421143 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.3057. Min Act: -0.0000

Data Index: 839447 (The Pile)

Max Activating Token Index: 1002

Text #19

Max Range: 0.3957. Min Range: -0.3957

Max Act: 0.2901. Min Act: -0.0000

Data Index: 317125 (The Pile)

Max Activating Token Index: 168