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

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

Neuron 5345 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.5000. Min Act: -0.0000

Data Index: 303329 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.5255. Min Act: -0.0000

Data Index: 543916 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4753. Min Act: -0.0000

Data Index: 915454 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4273. Min Act: -0.0000

Data Index: 832360 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1115952 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4145. Min Act: -0.0000

Data Index: 774882 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4103. Min Act: -0.0000

Data Index: 675439 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4152. Min Act: -0.0000

Data Index: 398933 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3900. Min Act: -0.0000

Data Index: 139643 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3930. Min Act: -0.0000

Data Index: 942317 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1300449 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3192. Min Act: -0.0000

Data Index: 641416 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3847. Min Act: -0.0000

Data Index: 322345 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3882. Min Act: -0.0000

Data Index: 751227 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3703. Min Act: -0.0000

Data Index: 991102 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3596. Min Act: -0.0000

Data Index: 792092 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3836. Min Act: -0.0000

Data Index: 780159 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3381. Min Act: -0.0000

Data Index: 578702 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3329. Min Act: -0.0000

Data Index: 50887 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3438. Min Act: -0.0000

Data Index: 909212 (C4 (Web Text))

Max Activating Token Index: 41