Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2757 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4860. Min Act: -0.0000

Data Index: 426107 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4515. Min Act: -0.0000

Data Index: 439168 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1261448 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4604. Min Act: 0.0000

Data Index: 78092 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1087304 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4222. Min Act: -0.0000

Data Index: 468637 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.4208. Min Act: 0.0000

Data Index: 712872 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3837. Min Act: -0.0000

Data Index: 98688 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1259151 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3736. Min Act: 0.0002

Data Index: 738379 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3632. Min Act: -0.0000

Data Index: 259581 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3387. Min Act: -0.0000

Data Index: 749811 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3460. Min Act: -0.0000

Data Index: 181946 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3470. Min Act: 0.0000

Data Index: 968928 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3439. Min Act: -0.0000

Data Index: 299864 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1162243 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3389. Min Act: -0.0000

Data Index: 199429 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3264. Min Act: 0.0000

Data Index: 1296096 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1180461 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.4860. Min Range: -0.4860

Max Act: 0.2988. Min Act: -0.0000

Data Index: 393756 (C4 (Web Text))

Max Activating Token Index: 186