Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3474 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5366. Min Range: -2.5366

Max Act: 2.5366. Min Act: -0.0000

Data Index: 1449710 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 2.5366. Min Range: -2.5366

Max Act: 2.3738. Min Act: -0.0000

Data Index: 1562506 (Python Code)

Max Activating Token Index: 414

Text #2

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.8019. Min Act: -0.0000

Data Index: 1562794 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.5568. Min Act: -0.0000

Data Index: 1507806 (Python Code)

Max Activating Token Index: 252

Text #4

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1333124 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.5233. Min Act: -0.0000

Data Index: 1456212 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.4997. Min Act: -0.0000

Data Index: 494570 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.4625. Min Act: -0.0000

Data Index: 1372403 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.3693. Min Act: -0.0000

Data Index: 350179 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1462069 (Python Code)

Max Activating Token Index: 588

Text #10

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1467362 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.4399. Min Act: -0.0000

Data Index: 1425221 (Python Code)

Max Activating Token Index: 160

Text #12

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.3571. Min Act: -0.0000

Data Index: 1527761 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1549518 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1506983 (Python Code)

Max Activating Token Index: 155

Text #15

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.2972. Min Act: -0.0000

Data Index: 1476889 (Python Code)

Max Activating Token Index: 507

Text #16

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.2400. Min Act: -0.0000

Data Index: 1529575 (Python Code)

Max Activating Token Index: 226

Text #17

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.2894. Min Act: -0.0000

Data Index: 1463235 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.2343. Min Act: -0.0000

Data Index: 1649222 (Python Code)

Max Activating Token Index: 822

Text #19

Max Range: 2.5366. Min Range: -2.5366

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1532548 (Python Code)

Max Activating Token Index: 296