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

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

Neuron 621 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.2857. Min Act: -0.0000

Data Index: 589172 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.0338. Min Act: -0.0000

Data Index: 507380 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.0214. Min Act: -0.0000

Data Index: 658958 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.9300. Min Act: 0.0001

Data Index: 315049 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 1.2857. Min Range: -1.2857

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1277766 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.8616. Min Act: -0.0000

Data Index: 675985 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1057838 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.8835. Min Act: -0.0000

Data Index: 49781 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.8434. Min Act: -0.0000

Data Index: 907760 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.8329. Min Act: -0.0000

Data Index: 603430 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.8254. Min Act: -0.0000

Data Index: 938119 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.7949. Min Act: 0.0000

Data Index: 594724 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.8116. Min Act: 0.0001

Data Index: 998949 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.7532. Min Act: 0.0001

Data Index: 688155 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.8203. Min Act: -0.0000

Data Index: 43154 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.7670. Min Act: -0.0000

Data Index: 683015 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.7308. Min Act: 0.0000

Data Index: 819325 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.7369. Min Act: -0.0000

Data Index: 286422 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.7109. Min Act: -0.0000

Data Index: 199996 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 1.2857. Min Range: -1.2857

Max Act: 0.7015. Min Act: -0.0000

Data Index: 570784 (C4 (Web Text))

Max Activating Token Index: 716