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

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

Neuron 178 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1050081 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5677. Min Act: -0.0001

Data Index: 1261710 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5425. Min Act: -0.0001

Data Index: 624943 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1042766 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5274. Min Act: -0.0001

Data Index: 1320300 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4590. Min Act: -0.0001

Data Index: 668797 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4915. Min Act: 0.0000

Data Index: 359464 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4859. Min Act: -0.0001

Data Index: 1041684 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4719. Min Act: -0.0001

Data Index: 536165 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4834. Min Act: -0.0001

Data Index: 756980 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1311569 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4442. Min Act: -0.0001

Data Index: 374901 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4503. Min Act: -0.0001

Data Index: 1345637 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4635. Min Act: -0.0001

Data Index: 789903 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4345. Min Act: -0.0001

Data Index: 1148067 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4347. Min Act: -0.0001

Data Index: 751 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4130. Min Act: -0.0001

Data Index: 1179015 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4263. Min Act: -0.0001

Data Index: 446868 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4247. Min Act: -0.0001

Data Index: 342539 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4557. Min Act: -0.0001

Data Index: 452306 (C4 (Web Text))

Max Activating Token Index: 521