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

Dataset: The Pile

Neuron 1283 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: 0.6061. Min Range: -0.6061

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1009044 (The Pile)

Max Activating Token Index: 514

Text #1

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1674107 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3725. Min Act: -0.0000

Data Index: 589102 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3774. Min Act: -0.0000

Data Index: 186611 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3595. Min Act: -0.0000

Data Index: 433087 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1021031 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1660566 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3442. Min Act: -0.0000

Data Index: 80434 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1400212 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3352. Min Act: -0.0000

Data Index: 911361 (The Pile)

Max Activating Token Index: 204

Text #10

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.2885. Min Act: -0.0000

Data Index: 440798 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1320707 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1067483 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3146. Min Act: -0.0000

Data Index: 465021 (The Pile)

Max Activating Token Index: 27

Text #14

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1083060 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1218418 (The Pile)

Max Activating Token Index: 454

Text #16

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1072010 (The Pile)

Max Activating Token Index: 539

Text #17

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1320644 (The Pile)

Max Activating Token Index: 275

Text #18

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1085709 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1420540 (The Pile)

Max Activating Token Index: 962