Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2946 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.4069. Min Act: -0.0001

Data Index: 1437292 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.2632. Min Act: -0.0001

Data Index: 1475427 (Python Code)

Max Activating Token Index: 512

Text #2

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0812. Min Act: -0.0001

Data Index: 1646309 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0654. Min Act: -0.0001

Data Index: 1418158 (Python Code)

Max Activating Token Index: 740

Text #4

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0552. Min Act: -0.0001

Data Index: 1513313 (Python Code)

Max Activating Token Index: 729

Text #5

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0565. Min Act: -0.0001

Data Index: 1628323 (Python Code)

Max Activating Token Index: 654

Text #6

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0386. Min Act: -0.0001

Data Index: 1408698 (Python Code)

Max Activating Token Index: 991

Text #7

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0070. Min Act: -0.0001

Data Index: 1378287 (Python Code)

Max Activating Token Index: 973

Text #8

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0238. Min Act: -0.0001

Data Index: 1390359 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0258. Min Act: -0.0001

Data Index: 1519087 (Python Code)

Max Activating Token Index: 405

Text #10

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.9620. Min Act: -0.0001

Data Index: 1592543 (Python Code)

Max Activating Token Index: 791

Text #11

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0402. Min Act: -0.0001

Data Index: 1578325 (Python Code)

Max Activating Token Index: 472

Text #12

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0715. Min Act: -0.0001

Data Index: 1390851 (Python Code)

Max Activating Token Index: 527

Text #13

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0240. Min Act: -0.0001

Data Index: 1511739 (Python Code)

Max Activating Token Index: 455

Text #14

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0317. Min Act: -0.0001

Data Index: 1454757 (Python Code)

Max Activating Token Index: 948

Text #15

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0959. Min Act: -0.0001

Data Index: 1648549 (Python Code)

Max Activating Token Index: 900

Text #16

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0373. Min Act: -0.0001

Data Index: 1474469 (Python Code)

Max Activating Token Index: 504

Text #17

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.9865. Min Act: -0.0001

Data Index: 1580497 (Python Code)

Max Activating Token Index: 281

Text #18

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.9885. Min Act: -0.0001

Data Index: 1456874 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.9832. Min Act: -0.0001

Data Index: 1644092 (Python Code)

Max Activating Token Index: 541