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

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

Neuron 714 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3949. Min Range: -2.3949

Max Act: 2.3949. Min Act: -0.0000

Data Index: 1550448 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 2.3949. Min Range: -2.3949

Max Act: 2.2282. Min Act: -0.0000

Data Index: 1471847 (Python Code)

Max Activating Token Index: 473

Text #2

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.9780. Min Act: -0.0000

Data Index: 1386618 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 2.3949. Min Range: -2.3949

Max Act: 2.0911. Min Act: -0.0000

Data Index: 1404636 (Python Code)

Max Activating Token Index: 352

Text #4

Max Range: 2.3949. Min Range: -2.3949

Max Act: 2.0768. Min Act: -0.0000

Data Index: 1465071 (Python Code)

Max Activating Token Index: 942

Text #5

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.9340. Min Act: -0.0000

Data Index: 1608738 (Python Code)

Max Activating Token Index: 606

Text #6

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1583605 (Python Code)

Max Activating Token Index: 967

Text #7

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.8627. Min Act: -0.0000

Data Index: 1501306 (Python Code)

Max Activating Token Index: 807

Text #8

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.8640. Min Act: -0.0000

Data Index: 1648258 (Python Code)

Max Activating Token Index: 125

Text #9

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.8658. Min Act: -0.0000

Data Index: 1363066 (Python Code)

Max Activating Token Index: 42

Text #10

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.7731. Min Act: -0.0000

Data Index: 1393028 (Python Code)

Max Activating Token Index: 433

Text #11

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1580589 (Python Code)

Max Activating Token Index: 803

Text #12

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.7387. Min Act: -0.0000

Data Index: 1576176 (Python Code)

Max Activating Token Index: 486

Text #13

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.8288. Min Act: -0.0000

Data Index: 1552745 (Python Code)

Max Activating Token Index: 149

Text #14

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.6428. Min Act: -0.0000

Data Index: 1444887 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.8291. Min Act: -0.0000

Data Index: 1595107 (Python Code)

Max Activating Token Index: 230

Text #16

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.6105. Min Act: -0.0000

Data Index: 1527580 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.7487. Min Act: -0.0000

Data Index: 1400146 (Python Code)

Max Activating Token Index: 280

Text #18

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.6661. Min Act: -0.0000

Data Index: 1398062 (Python Code)

Max Activating Token Index: 508

Text #19

Max Range: 2.3949. Min Range: -2.3949

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1505122 (Python Code)

Max Activating Token Index: 317