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

Dataset: The Pile

Neuron 1488 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: 0.4514. Min Range: -0.4514

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1393229 (The Pile)

Max Activating Token Index: 150

Text #1

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1792338 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3811. Min Act: -0.0000

Data Index: 237659 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3313. Min Act: -0.0000

Data Index: 579215 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3428. Min Act: -0.0000

Data Index: 116142 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1451181 (The Pile)

Max Activating Token Index: 704

Text #6

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1136637 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1291965 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1414065 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3045. Min Act: -0.0000

Data Index: 616825 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1219396 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1695812 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2959. Min Act: -0.0000

Data Index: 371892 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1159955 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3781. Min Act: -0.0000

Data Index: 341460 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2929. Min Act: -0.0000

Data Index: 77606 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3002. Min Act: -0.0000

Data Index: 296162 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2740. Min Act: -0.0000

Data Index: 667059 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1981004 (The Pile)

Max Activating Token Index: 514

Text #19

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1643218 (The Pile)

Max Activating Token Index: 863