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

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

Neuron 3844 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.6255. Min Act: -0.0001

Data Index: 565376 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.4935. Min Act: -0.0001

Data Index: 227718 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.3735. Min Act: -0.0001

Data Index: 504217 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5264. Min Act: -0.0001

Data Index: 1175851 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.4706. Min Act: -0.0001

Data Index: 798802 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.4236. Min Act: -0.0001

Data Index: 358731 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.4888. Min Act: -0.0001

Data Index: 1160702 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.4290. Min Act: -0.0001

Data Index: 355583 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.2800. Min Act: -0.0001

Data Index: 21208 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.4230. Min Act: -0.0001

Data Index: 653258 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.3949. Min Act: -0.0001

Data Index: 785462 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.3009. Min Act: -0.0001

Data Index: 158640 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.3021. Min Act: -0.0001

Data Index: 978859 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.3075. Min Act: -0.0001

Data Index: 1302641 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.2857. Min Act: -0.0001

Data Index: 437186 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.2304. Min Act: -0.0001

Data Index: 609821 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.2481. Min Act: -0.0001

Data Index: 845106 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.2773. Min Act: -0.0001

Data Index: 411814 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.2285. Min Act: -0.0001

Data Index: 83954 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.1561. Min Act: -0.0001

Data Index: 1074395 (C4 (Web Text))

Max Activating Token Index: 325