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

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

Neuron 2814 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4187. Min Range: -3.4187

Max Act: 3.4187. Min Act: -0.0001

Data Index: 748943 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 3.4187. Min Range: -3.4187

Max Act: 3.1968. Min Act: -0.0001

Data Index: 824393 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 3.4187. Min Range: -3.4187

Max Act: 3.0147. Min Act: -0.0001

Data Index: 733468 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.9408. Min Act: -0.0001

Data Index: 415668 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 3.4187. Min Range: -3.4187

Max Act: 3.1992. Min Act: -0.0001

Data Index: 251081 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.8588. Min Act: -0.0001

Data Index: 398486 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.8265. Min Act: -0.0001

Data Index: 746578 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.8760. Min Act: -0.0001

Data Index: 547633 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.6595. Min Act: -0.0001

Data Index: 571710 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.4406. Min Act: -0.0001

Data Index: 761883 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.5307. Min Act: -0.0001

Data Index: 926414 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.6093. Min Act: -0.0001

Data Index: 703466 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.6099. Min Act: -0.0001

Data Index: 1313824 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.7423. Min Act: -0.0001

Data Index: 1314956 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.5356. Min Act: -0.0001

Data Index: 467923 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.6931. Min Act: -0.0001

Data Index: 670800 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.5451. Min Act: -0.0001

Data Index: 481828 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.7522. Min Act: -0.0001

Data Index: 362989 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.5527. Min Act: -0.0001

Data Index: 1000239 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 3.4187. Min Range: -3.4187

Max Act: 2.6548. Min Act: -0.0001

Data Index: 1024337 (C4 (Web Text))

Max Activating Token Index: 799