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

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

Neuron 3090 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: 2.9680. Min Range: -2.9680

Max Act: 2.9680. Min Act: -0.0000

Data Index: 1465234 (Python Code)

Max Activating Token Index: 167

Text #1

Max Range: 2.9680. Min Range: -2.9680

Max Act: 2.6831. Min Act: -0.0000

Data Index: 1388272 (Python Code)

Max Activating Token Index: 285

Text #2

Max Range: 2.9680. Min Range: -2.9680

Max Act: 2.6010. Min Act: -0.0000

Data Index: 1408851 (Python Code)

Max Activating Token Index: 652

Text #3

Max Range: 2.9680. Min Range: -2.9680

Max Act: 2.0351. Min Act: -0.0000

Data Index: 1470136 (Python Code)

Max Activating Token Index: 967

Text #4

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.8917. Min Act: -0.0000

Data Index: 1410052 (Python Code)

Max Activating Token Index: 549

Text #5

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.8356. Min Act: -0.0000

Data Index: 1633243 (Python Code)

Max Activating Token Index: 723

Text #6

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.9060. Min Act: -0.0000

Data Index: 1579446 (Python Code)

Max Activating Token Index: 968

Text #7

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.6968. Min Act: -0.0000

Data Index: 1640822 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.7487. Min Act: -0.0000

Data Index: 1531401 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.6134. Min Act: -0.0000

Data Index: 1567492 (Python Code)

Max Activating Token Index: 636

Text #10

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.5840. Min Act: -0.0000

Data Index: 1638571 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.4538. Min Act: -0.0000

Data Index: 1653303 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.6420. Min Act: -0.0000

Data Index: 1436929 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.5097. Min Act: -0.0000

Data Index: 1503829 (Python Code)

Max Activating Token Index: 635

Text #14

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.5036. Min Act: -0.0000

Data Index: 1509197 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.5793. Min Act: -0.0000

Data Index: 1497757 (Python Code)

Max Activating Token Index: 360

Text #16

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1651095 (Python Code)

Max Activating Token Index: 513

Text #17

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.4294. Min Act: -0.0000

Data Index: 1361598 (Python Code)

Max Activating Token Index: 570

Text #18

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.4409. Min Act: -0.0000

Data Index: 1611656 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 2.9680. Min Range: -2.9680

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1375534 (Python Code)

Max Activating Token Index: 119