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

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

Neuron 259 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: 1.8394. Min Range: -1.8394

Max Act: 1.8209. Min Act: -0.0000

Data Index: 831075 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.8189. Min Act: -0.0000

Data Index: 715499 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.8394. Min Act: -0.0000

Data Index: 619891 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.6694. Min Act: -0.0000

Data Index: 1396929 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.6350. Min Act: -0.0000

Data Index: 1561246 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.5550. Min Act: -0.0000

Data Index: 865540 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.4049. Min Act: -0.0000

Data Index: 817986 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.5264. Min Act: -0.0000

Data Index: 1440356 (Python Code)

Max Activating Token Index: 533

Text #8

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.5576. Min Act: -0.0000

Data Index: 710461 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1160340 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1285497 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.4766. Min Act: -0.0000

Data Index: 646096 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.5563. Min Act: -0.0000

Data Index: 83877 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1178650 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.2727. Min Act: -0.0000

Data Index: 1377022 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.3103. Min Act: -0.0000

Data Index: 512257 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.3802. Min Act: -0.0000

Data Index: 5709 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.2833. Min Act: -0.0000

Data Index: 489126 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.3584. Min Act: -0.0000

Data Index: 1013755 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 1.8394. Min Range: -1.8394

Max Act: 1.3354. Min Act: -0.0000

Data Index: 800677 (C4 (Web Text))

Max Activating Token Index: 875