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

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

Neuron 4154 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: 2.0367. Min Range: -2.0367

Max Act: 2.0367. Min Act: -0.0000

Data Index: 526028 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.8331. Min Act: -0.0000

Data Index: 566333 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.7341. Min Act: -0.0000

Data Index: 937981 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.6793. Min Act: -0.0000

Data Index: 714813 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.8854. Min Act: -0.0000

Data Index: 326628 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.7808. Min Act: -0.0000

Data Index: 929600 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.7278. Min Act: -0.0000

Data Index: 1100084 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.7706. Min Act: -0.0000

Data Index: 890235 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.8048. Min Act: -0.0000

Data Index: 666874 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.7891. Min Act: -0.0000

Data Index: 259036 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.8297. Min Act: -0.0000

Data Index: 594651 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.7731. Min Act: -0.0000

Data Index: 229217 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.7799. Min Act: -0.0000

Data Index: 817625 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.6674. Min Act: -0.0000

Data Index: 1060833 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.6564. Min Act: -0.0000

Data Index: 1116044 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.7455. Min Act: -0.0000

Data Index: 968593 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.7329. Min Act: -0.0000

Data Index: 454405 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.6886. Min Act: -0.0000

Data Index: 1323756 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.7749. Min Act: -0.0000

Data Index: 1053149 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 2.0367. Min Range: -2.0367

Max Act: 1.6362. Min Act: -0.0000

Data Index: 412190 (C4 (Web Text))

Max Activating Token Index: 539