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

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

Neuron 4396 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0944. Min Range: -1.0944

Max Act: 1.0944. Min Act: -0.0000

Data Index: 898788 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1211081 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.8981. Min Act: -0.0000

Data Index: 328221 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1179791 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1175642 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.7995. Min Act: -0.0000

Data Index: 206043 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.8618. Min Act: -0.0000

Data Index: 450799 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1044395 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.9433. Min Act: -0.0000

Data Index: 187069 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.8177. Min Act: -0.0000

Data Index: 383421 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1227774 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.7837. Min Act: -0.0000

Data Index: 86491 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.8001. Min Act: -0.0000

Data Index: 626760 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1351770 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1231398 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.7865. Min Act: -0.0000

Data Index: 687732 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1264248 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.7691. Min Act: -0.0000

Data Index: 191167 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1147168 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 1.0944. Min Range: -1.0944

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1846 (C4 (Web Text))

Max Activating Token Index: 484