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

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

Neuron 450 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.5252. Min Act: -0.0001

Data Index: 1412554 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4351. Min Act: -0.0001

Data Index: 1610230 (Python Code)

Max Activating Token Index: 513

Text #2

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4345. Min Act: -0.0001

Data Index: 1619306 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4698. Min Act: -0.0001

Data Index: 1604093 (Python Code)

Max Activating Token Index: 1020

Text #4

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4348. Min Act: -0.0001

Data Index: 1403875 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4695. Min Act: -0.0001

Data Index: 1599493 (Python Code)

Max Activating Token Index: 905

Text #6

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4352. Min Act: -0.0001

Data Index: 1614358 (Python Code)

Max Activating Token Index: 488

Text #7

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4445. Min Act: -0.0001

Data Index: 1511110 (Python Code)

Max Activating Token Index: 477

Text #8

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4439. Min Act: -0.0001

Data Index: 1403235 (Python Code)

Max Activating Token Index: 780

Text #9

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4416. Min Act: -0.0001

Data Index: 1417019 (Python Code)

Max Activating Token Index: 588

Text #10

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1509773 (Python Code)

Max Activating Token Index: 890

Text #11

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4249. Min Act: -0.0001

Data Index: 1406694 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4199. Min Act: -0.0001

Data Index: 1379322 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4308. Min Act: -0.0001

Data Index: 1583784 (Python Code)

Max Activating Token Index: 793

Text #14

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1596073 (Python Code)

Max Activating Token Index: 230

Text #15

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4144. Min Act: -0.0001

Data Index: 1630600 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3985. Min Act: -0.0001

Data Index: 1418102 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4251. Min Act: -0.0001

Data Index: 1603703 (Python Code)

Max Activating Token Index: 334

Text #18

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.3901. Min Act: -0.0001

Data Index: 1638410 (Python Code)

Max Activating Token Index: 613

Text #19

Max Range: 0.5252. Min Range: -0.5252

Max Act: 0.4016. Min Act: -0.0001

Data Index: 1541370 (Python Code)

Max Activating Token Index: 329