Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2243 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.4104. Min Act: -0.0001

Data Index: 765142 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3934. Min Act: -0.0000

Data Index: 782376 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1810497 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3732. Min Act: -0.0001

Data Index: 807355 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3453. Min Act: -0.0001

Data Index: 388174 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3374. Min Act: -0.0000

Data Index: 62851 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1555994 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3375. Min Act: -0.0000

Data Index: 649336 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1943570 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1969016 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3237. Min Act: -0.0000

Data Index: 97476 (The Pile)

Max Activating Token Index: 907

Text #11

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.3110. Min Act: -0.0000

Data Index: 122849 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.2982. Min Act: -0.0000

Data Index: 894288 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.2989. Min Act: -0.0000

Data Index: 829465 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.2901. Min Act: -0.0001

Data Index: 486019 (The Pile)

Max Activating Token Index: 907

Text #15

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.2792. Min Act: -0.0001

Data Index: 1035052 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1579406 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.2875. Min Act: -0.0000

Data Index: 887177 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.2912. Min Act: -0.0000

Data Index: 743778 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 0.4104. Min Range: -0.4104

Max Act: 0.2721. Min Act: -0.0001

Data Index: 922908 (The Pile)

Max Activating Token Index: 748