Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1186 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3772. Min Act: -0.0001

Data Index: 1636 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3264. Min Act: -0.0001

Data Index: 1255260 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3334. Min Act: -0.0000

Data Index: 194827 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.3495. Min Act: -0.0001

Data Index: 626121 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2965. Min Act: -0.0001

Data Index: 923564 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2825. Min Act: -0.0001

Data Index: 456409 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2881. Min Act: -0.0001

Data Index: 664432 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2674. Min Act: 0.0005

Data Index: 340907 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2843. Min Act: -0.0001

Data Index: 689074 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2509. Min Act: -0.0001

Data Index: 828089 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2520. Min Act: 0.0002

Data Index: 770023 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2494. Min Act: -0.0001

Data Index: 1305891 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2431. Min Act: -0.0001

Data Index: 478538 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2348. Min Act: 0.0002

Data Index: 526206 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2419. Min Act: 0.0002

Data Index: 651431 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2448. Min Act: 0.0002

Data Index: 552403 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2283. Min Act: 0.0003

Data Index: 89100 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2290. Min Act: 0.0004

Data Index: 397659 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2269. Min Act: -0.0000

Data Index: 647868 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.3772. Min Range: -0.3772

Max Act: 0.2237. Min Act: 0.0000

Data Index: 534665 (C4 (Web Text))

Max Activating Token Index: 278