Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1613 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.5708. Min Act: -0.0000

Data Index: 382726 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1213608 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4859. Min Act: -0.0000

Data Index: 795397 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1022445 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4671. Min Act: -0.0000

Data Index: 325223 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4776. Min Act: -0.0000

Data Index: 216523 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4422. Min Act: -0.0000

Data Index: 844784 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.4059. Min Act: -0.0000

Data Index: 229489 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3999. Min Act: -0.0000

Data Index: 231226 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1041736 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3760. Min Act: -0.0000

Data Index: 709288 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3664. Min Act: -0.0000

Data Index: 384659 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1259305 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3698. Min Act: -0.0000

Data Index: 376750 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3425. Min Act: -0.0000

Data Index: 602500 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3406. Min Act: -0.0000

Data Index: 852531 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3239. Min Act: -0.0000

Data Index: 658641 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3284. Min Act: -0.0000

Data Index: 635176 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3337. Min Act: 0.0001

Data Index: 438172 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.5708. Min Range: -0.5708

Max Act: 0.3215. Min Act: -0.0000

Data Index: 66781 (C4 (Web Text))

Max Activating Token Index: 915