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

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

Neuron 4487 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.5013. Min Act: -0.0001

Data Index: 1160162 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.5860. Min Act: -0.0000

Data Index: 1516500 (Python Code)

Max Activating Token Index: 810

Text #2

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.2614. Min Act: -0.0000

Data Index: 1429923 (Python Code)

Max Activating Token Index: 181

Text #3

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9707. Min Act: -0.0001

Data Index: 596249 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.0604. Min Act: -0.0001

Data Index: 1498574 (Python Code)

Max Activating Token Index: 1016

Text #5

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.0221. Min Act: -0.0000

Data Index: 1570813 (Python Code)

Max Activating Token Index: 298

Text #6

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9646. Min Act: -0.0000

Data Index: 67846 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.8631. Min Act: -0.0001

Data Index: 1584907 (Python Code)

Max Activating Token Index: 59

Text #8

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.5701. Min Act: -0.0001

Data Index: 194161 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.1659. Min Act: -0.0000

Data Index: 1465031 (Python Code)

Max Activating Token Index: 449

Text #10

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.9180. Min Act: -0.0001

Data Index: 1415056 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.6467. Min Act: -0.0001

Data Index: 1458206 (Python Code)

Max Activating Token Index: 409

Text #12

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.8315. Min Act: -0.0001

Data Index: 1518685 (Python Code)

Max Activating Token Index: 128

Text #13

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.7104. Min Act: -0.0000

Data Index: 1522706 (Python Code)

Max Activating Token Index: 996

Text #14

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.6854. Min Act: -0.0000

Data Index: 1480648 (Python Code)

Max Activating Token Index: 583

Text #15

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.6334. Min Act: -0.0000

Data Index: 1456288 (Python Code)

Max Activating Token Index: 248

Text #16

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.5837. Min Act: -0.0000

Data Index: 1572076 (Python Code)

Max Activating Token Index: 541

Text #17

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.6464. Min Act: -0.0000

Data Index: 1534586 (Python Code)

Max Activating Token Index: 628

Text #18

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.5587. Min Act: -0.0000

Data Index: 1380310 (Python Code)

Max Activating Token Index: 617

Text #19

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.7254. Min Act: -0.0000

Data Index: 1550118 (Python Code)

Max Activating Token Index: 729