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

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

Neuron 2976 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.5514. Min Act: -0.0000

Data Index: 1158561 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 4.5514. Min Range: -4.5514

Max Act: 4.3679. Min Act: -0.0000

Data Index: 1358098 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.8674. Min Act: -0.0001

Data Index: 744575 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.6391. Min Act: -0.0001

Data Index: 1134005 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.8881. Min Act: -0.0001

Data Index: 372130 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.5051. Min Act: -0.0001

Data Index: 241026 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.6750. Min Act: -0.0000

Data Index: 444620 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.5657. Min Act: -0.0000

Data Index: 1120382 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.4111. Min Act: -0.0000

Data Index: 925014 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.5389. Min Act: -0.0000

Data Index: 665577 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.5585. Min Act: -0.0000

Data Index: 960732 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.1165. Min Act: -0.0001

Data Index: 406931 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.1125. Min Act: -0.0000

Data Index: 1152705 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.0685. Min Act: -0.0000

Data Index: 360777 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.5257. Min Act: -0.0000

Data Index: 1226169 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.0732. Min Act: -0.0001

Data Index: 909261 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.2308. Min Act: -0.0000

Data Index: 245097 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.3630. Min Act: -0.0000

Data Index: 567936 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.0654. Min Act: -0.0000

Data Index: 320909 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 4.5514. Min Range: -4.5514

Max Act: 3.4485. Min Act: -0.0000

Data Index: 574128 (C4 (Web Text))

Max Activating Token Index: 689