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

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

Neuron 3307 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5642. Min Act: -0.0001

Data Index: 397780 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5434. Min Act: -0.0001

Data Index: 1261432 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5163. Min Act: -0.0000

Data Index: 457310 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4933. Min Act: -0.0000

Data Index: 879138 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1190873 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5031. Min Act: -0.0000

Data Index: 313364 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4940. Min Act: -0.0001

Data Index: 849222 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1030418 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5059. Min Act: -0.0000

Data Index: 304072 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4611. Min Act: -0.0000

Data Index: 454544 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4257. Min Act: -0.0001

Data Index: 1030742 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4342. Min Act: -0.0000

Data Index: 179983 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4473. Min Act: -0.0001

Data Index: 257562 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1294573 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4264. Min Act: -0.0000

Data Index: 479952 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4126. Min Act: -0.0000

Data Index: 427523 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4104. Min Act: -0.0000

Data Index: 562036 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1126260 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4135. Min Act: -0.0000

Data Index: 269361 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3966. Min Act: -0.0000

Data Index: 989633 (C4 (Web Text))

Max Activating Token Index: 325