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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 976 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.3386. Min Act: -0.0000

Data Index: 1131784 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.4545. Min Act: -0.0000

Data Index: 1310225 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.2352. Min Act: -0.0000

Data Index: 1338363 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.4120. Min Act: -0.0000

Data Index: 1277810 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.3227. Min Act: -0.0000

Data Index: 600202 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.3548. Min Act: -0.0000

Data Index: 1346249 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.1921. Min Act: -0.0000

Data Index: 1180826 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.1909. Min Act: -0.0000

Data Index: 606799 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.0516. Min Act: -0.0000

Data Index: 1110105 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.3580. Min Act: -0.0000

Data Index: 204523 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.0281. Min Act: -0.0000

Data Index: 321262 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.0815. Min Act: -0.0000

Data Index: 1123368 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.0675. Min Act: -0.0000

Data Index: 1133844 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.1549. Min Act: -0.0000

Data Index: 478950 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 2.4545. Min Range: -2.4545

Max Act: 1.9146. Min Act: -0.0000

Data Index: 497932 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.0118. Min Act: -0.0000

Data Index: 826730 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.1028. Min Act: -0.0000

Data Index: 90391 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 2.4545. Min Range: -2.4545

Max Act: 1.8852. Min Act: -0.0000

Data Index: 149461 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 2.4545. Min Range: -2.4545

Max Act: 1.7470. Min Act: -0.0000

Data Index: 699682 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 2.4545. Min Range: -2.4545

Max Act: 2.0755. Min Act: -0.0000

Data Index: 1002766 (C4 (Web Text))

Max Activating Token Index: 579