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

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

Neuron 1210 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: 1.4857. Min Range: -1.4857

Max Act: 1.4857. Min Act: -0.0001

Data Index: 3509 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.4728. Min Act: -0.0001

Data Index: 270705 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.4845. Min Act: -0.0001

Data Index: 618539 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.4449. Min Act: -0.0001

Data Index: 559254 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.2572. Min Act: -0.0000

Data Index: 258511 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.1721. Min Act: -0.0001

Data Index: 295596 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.2555. Min Act: -0.0001

Data Index: 1104292 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.2158. Min Act: -0.0001

Data Index: 1237080 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.1411. Min Act: -0.0001

Data Index: 455839 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.1817. Min Act: -0.0001

Data Index: 760735 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.1265. Min Act: -0.0001

Data Index: 461755 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0996. Min Act: -0.0001

Data Index: 487901 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0923. Min Act: -0.0001

Data Index: 796570 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.1387. Min Act: -0.0001

Data Index: 307936 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0810. Min Act: -0.0001

Data Index: 1176434 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0012. Min Act: -0.0001

Data Index: 443355 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0933. Min Act: -0.0001

Data Index: 1299624 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.4857. Min Range: -1.4857

Max Act: 0.9618. Min Act: -0.0001

Data Index: 69306 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 1.4857. Min Range: -1.4857

Max Act: 1.0116. Min Act: -0.0001

Data Index: 561951 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 1.4857. Min Range: -1.4857

Max Act: 0.9736. Min Act: -0.0001

Data Index: 704355 (C4 (Web Text))

Max Activating Token Index: 256