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

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

Neuron 1412 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4156. Min Range: -3.4156

Max Act: 3.2445. Min Act: -0.0001

Data Index: 568035 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 3.4156. Min Range: -3.4156

Max Act: 3.2392. Min Act: -0.0001

Data Index: 757450 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 3.4156. Min Range: -3.4156

Max Act: 3.4156. Min Act: -0.0001

Data Index: 377872 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 3.4156. Min Range: -3.4156

Max Act: 3.2367. Min Act: -0.0001

Data Index: 1230645 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 3.4156. Min Range: -3.4156

Max Act: 3.2654. Min Act: -0.0001

Data Index: 185729 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 3.4156. Min Range: -3.4156

Max Act: 3.0879. Min Act: -0.0001

Data Index: 980611 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 3.4156. Min Range: -3.4156

Max Act: 3.2568. Min Act: -0.0001

Data Index: 1163832 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 3.4156. Min Range: -3.4156

Max Act: 3.3751. Min Act: -0.0001

Data Index: 963477 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 3.4156. Min Range: -3.4156

Max Act: 3.0100. Min Act: -0.0001

Data Index: 120810 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 3.4156. Min Range: -3.4156

Max Act: 2.9469. Min Act: -0.0001

Data Index: 873683 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 3.4156. Min Range: -3.4156

Max Act: 2.3387. Min Act: -0.0001

Data Index: 425157 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 3.4156. Min Range: -3.4156

Max Act: 2.2768. Min Act: -0.0001

Data Index: 98660 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 3.4156. Min Range: -3.4156

Max Act: 2.2013. Min Act: -0.0001

Data Index: 1322659 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 3.4156. Min Range: -3.4156

Max Act: 2.1706. Min Act: -0.0001

Data Index: 1217151 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 3.4156. Min Range: -3.4156

Max Act: 2.3429. Min Act: -0.0001

Data Index: 65656 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 3.4156. Min Range: -3.4156

Max Act: 2.0380. Min Act: -0.0001

Data Index: 1321046 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 3.4156. Min Range: -3.4156

Max Act: 2.3107. Min Act: -0.0001

Data Index: 1279951 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 3.4156. Min Range: -3.4156

Max Act: 2.0848. Min Act: -0.0001

Data Index: 580261 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 3.4156. Min Range: -3.4156

Max Act: 2.0946. Min Act: -0.0001

Data Index: 550812 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 3.4156. Min Range: -3.4156

Max Act: 1.9222. Min Act: -0.0001

Data Index: 734814 (C4 (Web Text))

Max Activating Token Index: 189