Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3584 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8712. Min Act: -0.0001

Data Index: 413069 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.8500. Min Act: -0.0001

Data Index: 165478 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.6781. Min Act: -0.0001

Data Index: 552711 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.5630. Min Act: -0.0001

Data Index: 1020086 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.5682. Min Act: -0.0001

Data Index: 353663 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.6043. Min Act: -0.0001

Data Index: 1067551 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.5571. Min Act: -0.0001

Data Index: 248726 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.4688. Min Act: -0.0001

Data Index: 296812 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.5882. Min Act: -0.0001

Data Index: 1416047 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.5213. Min Act: -0.0001

Data Index: 824416 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.5673. Min Act: -0.0001

Data Index: 627215 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.5756. Min Act: -0.0001

Data Index: 180395 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.4428. Min Act: -0.0001

Data Index: 245393 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.5607. Min Act: -0.0001

Data Index: 1048814 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.4925. Min Act: -0.0001

Data Index: 721930 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.4202. Min Act: -0.0001

Data Index: 1292356 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.4911. Min Act: -0.0001

Data Index: 594019 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.4380. Min Act: -0.0001

Data Index: 1461868 (Python Code)

Max Activating Token Index: 629

Text #18

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.4377. Min Act: -0.0001

Data Index: 463257 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 1.8712. Min Range: -1.8712

Max Act: 1.3931. Min Act: -0.0001

Data Index: 1372219 (Python Code)

Max Activating Token Index: 912