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

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

Neuron 1761 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4955. Min Act: -0.0000

Data Index: 859861 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1604689 (Python Code)

Max Activating Token Index: 492

Text #2

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1436358 (Python Code)

Max Activating Token Index: 347

Text #3

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4350. Min Act: -0.0000

Data Index: 886739 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4536. Min Act: -0.0000

Data Index: 442554 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1402408 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1525459 (Python Code)

Max Activating Token Index: 746

Text #7

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3992. Min Act: -0.0000

Data Index: 433206 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4439. Min Act: -0.0000

Data Index: 841881 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1413758 (Python Code)

Max Activating Token Index: 878

Text #10

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1579883 (Python Code)

Max Activating Token Index: 515

Text #11

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1383055 (Python Code)

Max Activating Token Index: 349

Text #12

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1462148 (Python Code)

Max Activating Token Index: 735

Text #13

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1479878 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1188170 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3856. Min Act: -0.0000

Data Index: 861107 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1651439 (Python Code)

Max Activating Token Index: 354

Text #17

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1511357 (Python Code)

Max Activating Token Index: 121

Text #18

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3683. Min Act: -0.0000

Data Index: 740479 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1084293 (C4 (Web Text))

Max Activating Token Index: 295