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

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

Neuron 3399 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2714. Min Range: -4.2714

Max Act: 4.1601. Min Act: -0.0000

Data Index: 1430631 (Python Code)

Max Activating Token Index: 546

Text #1

Max Range: 4.2714. Min Range: -4.2714

Max Act: 4.2714. Min Act: -0.0001

Data Index: 1620309 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 4.2714. Min Range: -4.2714

Max Act: 4.2578. Min Act: 0.0001

Data Index: 1554905 (Python Code)

Max Activating Token Index: 926

Text #3

Max Range: 4.2714. Min Range: -4.2714

Max Act: 4.0900. Min Act: -0.0001

Data Index: 1629524 (Python Code)

Max Activating Token Index: 563

Text #4

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.8613. Min Act: -0.0000

Data Index: 1388395 (Python Code)

Max Activating Token Index: 852

Text #5

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.8008. Min Act: -0.0001

Data Index: 1453737 (Python Code)

Max Activating Token Index: 522

Text #6

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.8782. Min Act: -0.0000

Data Index: 1654558 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 4.2714. Min Range: -4.2714

Max Act: 4.0415. Min Act: -0.0001

Data Index: 1443635 (Python Code)

Max Activating Token Index: 934

Text #8

Max Range: 4.2714. Min Range: -4.2714

Max Act: 4.1407. Min Act: -0.0000

Data Index: 1629563 (Python Code)

Max Activating Token Index: 711

Text #9

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.5915. Min Act: -0.0001

Data Index: 1463179 (Python Code)

Max Activating Token Index: 893

Text #10

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.7594. Min Act: -0.0000

Data Index: 1610196 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.8381. Min Act: -0.0001

Data Index: 1400402 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.6747. Min Act: -0.0001

Data Index: 1494492 (Python Code)

Max Activating Token Index: 573

Text #13

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.5146. Min Act: -0.0000

Data Index: 1532595 (Python Code)

Max Activating Token Index: 902

Text #14

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.4740. Min Act: 0.0001

Data Index: 1648085 (Python Code)

Max Activating Token Index: 158

Text #15

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.6099. Min Act: -0.0000

Data Index: 1496872 (Python Code)

Max Activating Token Index: 252

Text #16

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.4517. Min Act: -0.0000

Data Index: 1635441 (Python Code)

Max Activating Token Index: 611

Text #17

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.5621. Min Act: -0.0000

Data Index: 1520385 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.4207. Min Act: -0.0001

Data Index: 1394582 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 4.2714. Min Range: -4.2714

Max Act: 3.5387. Min Act: -0.0000

Data Index: 1637526 (Python Code)

Max Activating Token Index: 814