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

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

Neuron 2304 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0191. Min Range: -2.0191

Max Act: 2.0191. Min Act: -0.0000

Data Index: 175301 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.9996. Min Act: -0.0000

Data Index: 15467 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.8741. Min Act: -0.0000

Data Index: 942397 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.9022. Min Act: -0.0000

Data Index: 435467 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.9121. Min Act: -0.0000

Data Index: 1055715 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.6751. Min Act: -0.0000

Data Index: 999518 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.6801. Min Act: -0.0000

Data Index: 1323751 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.7349. Min Act: -0.0000

Data Index: 110246 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.6536. Min Act: -0.0000

Data Index: 1259146 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.7232. Min Act: -0.0000

Data Index: 747314 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.6750. Min Act: -0.0000

Data Index: 457768 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.6140. Min Act: -0.0000

Data Index: 898514 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.5963. Min Act: -0.0000

Data Index: 1311642 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.5946. Min Act: -0.0000

Data Index: 1027315 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.4417. Min Act: -0.0000

Data Index: 1108622 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.5435. Min Act: -0.0000

Data Index: 509523 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.5660. Min Act: -0.0000

Data Index: 407091 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.6371. Min Act: -0.0000

Data Index: 518793 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.4839. Min Act: -0.0000

Data Index: 982898 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 2.0191. Min Range: -2.0191

Max Act: 1.5651. Min Act: -0.0000

Data Index: 492512 (C4 (Web Text))

Max Activating Token Index: 228