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

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

Neuron 2414 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2234. Min Range: -5.2234

Max Act: 5.2234. Min Act: -0.0000

Data Index: 52793 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.6582. Min Act: -0.0000

Data Index: 1302524 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.3818. Min Act: -0.0000

Data Index: 758419 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.0659. Min Act: -0.0000

Data Index: 961462 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.4186. Min Act: -0.0000

Data Index: 766650 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.5868. Min Act: -0.0000

Data Index: 1347664 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.5020. Min Act: -0.0000

Data Index: 1218463 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.4733. Min Act: -0.0000

Data Index: 587498 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.3155. Min Act: -0.0000

Data Index: 15372 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.2738. Min Act: -0.0000

Data Index: 408331 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.3632. Min Act: -0.0000

Data Index: 314547 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.3554. Min Act: -0.0000

Data Index: 368521 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.1496. Min Act: -0.0000

Data Index: 742851 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.2940. Min Act: -0.0000

Data Index: 1339357 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.3070. Min Act: -0.0000

Data Index: 19734 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.2020. Min Act: -0.0000

Data Index: 780416 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.1840. Min Act: -0.0000

Data Index: 742907 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.1416. Min Act: -0.0000

Data Index: 400961 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.2550. Min Act: -0.0000

Data Index: 1291917 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 5.2234. Min Range: -5.2234

Max Act: 3.0743. Min Act: -0.0000

Data Index: 144321 (C4 (Web Text))

Max Activating Token Index: 44