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

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

Neuron 3488 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: 0.7086. Min Range: -0.7086

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1404854 (Python Code)

Max Activating Token Index: 813

Text #1

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1622036 (Python Code)

Max Activating Token Index: 874

Text #2

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1376635 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1501415 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1415157 (Python Code)

Max Activating Token Index: 960

Text #5

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1376374 (Python Code)

Max Activating Token Index: 591

Text #6

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1560408 (Python Code)

Max Activating Token Index: 440

Text #7

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1514487 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1367395 (Python Code)

Max Activating Token Index: 686

Text #9

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1446994 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1541809 (Python Code)

Max Activating Token Index: 457

Text #11

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1655046 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1426560 (Python Code)

Max Activating Token Index: 239

Text #13

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1509936 (Python Code)

Max Activating Token Index: 274

Text #14

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1406106 (Python Code)

Max Activating Token Index: 460

Text #15

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1545346 (Python Code)

Max Activating Token Index: 254

Text #16

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1447511 (Python Code)

Max Activating Token Index: 470

Text #17

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1607942 (Python Code)

Max Activating Token Index: 329

Text #18

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1557718 (Python Code)

Max Activating Token Index: 450

Text #19

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1601540 (Python Code)

Max Activating Token Index: 378