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

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

Neuron 4574 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2674. Min Range: -4.2674

Max Act: 4.2674. Min Act: -0.0000

Data Index: 1441148 (Python Code)

Max Activating Token Index: 414

Text #1

Max Range: 4.2674. Min Range: -4.2674

Max Act: 4.1084. Min Act: -0.0000

Data Index: 1539339 (Python Code)

Max Activating Token Index: 226

Text #2

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.7863. Min Act: -0.0000

Data Index: 1370460 (Python Code)

Max Activating Token Index: 656

Text #3

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.6170. Min Act: -0.0000

Data Index: 1599609 (Python Code)

Max Activating Token Index: 521

Text #4

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.8310. Min Act: -0.0000

Data Index: 1413169 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.4448. Min Act: -0.0000

Data Index: 1448487 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.4137. Min Act: -0.0000

Data Index: 1541427 (Python Code)

Max Activating Token Index: 948

Text #7

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.3906. Min Act: -0.0000

Data Index: 1403464 (Python Code)

Max Activating Token Index: 438

Text #8

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.3748. Min Act: -0.0000

Data Index: 1428641 (Python Code)

Max Activating Token Index: 224

Text #9

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.3484. Min Act: -0.0000

Data Index: 1545601 (Python Code)

Max Activating Token Index: 885

Text #10

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.2647. Min Act: -0.0000

Data Index: 1651824 (Python Code)

Max Activating Token Index: 727

Text #11

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.2124. Min Act: -0.0000

Data Index: 1611419 (Python Code)

Max Activating Token Index: 764

Text #12

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.0418. Min Act: -0.0000

Data Index: 1446449 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.4421. Min Act: -0.0000

Data Index: 1604728 (Python Code)

Max Activating Token Index: 759

Text #14

Max Range: 4.2674. Min Range: -4.2674

Max Act: 2.9831. Min Act: -0.0000

Data Index: 1600608 (Python Code)

Max Activating Token Index: 975

Text #15

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.2202. Min Act: -0.0000

Data Index: 1621152 (Python Code)

Max Activating Token Index: 629

Text #16

Max Range: 4.2674. Min Range: -4.2674

Max Act: 2.9866. Min Act: -0.0000

Data Index: 1592717 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 4.2674. Min Range: -4.2674

Max Act: 3.0990. Min Act: -0.0000

Data Index: 1565515 (Python Code)

Max Activating Token Index: 574

Text #18

Max Range: 4.2674. Min Range: -4.2674

Max Act: 2.6586. Min Act: -0.0000

Data Index: 1391418 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 4.2674. Min Range: -4.2674

Max Act: 2.9099. Min Act: -0.0000

Data Index: 1629972 (Python Code)

Max Activating Token Index: 54