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

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

Neuron 3768 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: 2.2740. Min Range: -2.2740

Max Act: 2.1696. Min Act: -0.0000

Data Index: 222471 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 2.2740. Min Range: -2.2740

Max Act: 2.2740. Min Act: -0.0000

Data Index: 1158184 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.9141. Min Act: -0.0000

Data Index: 110012 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 2.2740. Min Range: -2.2740

Max Act: 2.0568. Min Act: -0.0000

Data Index: 646875 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.8592. Min Act: -0.0000

Data Index: 1194408 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.8621. Min Act: -0.0000

Data Index: 59619 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.9585. Min Act: -0.0000

Data Index: 571330 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.7374. Min Act: -0.0000

Data Index: 785039 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.7299. Min Act: -0.0000

Data Index: 312927 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.7717. Min Act: -0.0000

Data Index: 744542 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.6992. Min Act: -0.0000

Data Index: 1213784 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.5867. Min Act: -0.0000

Data Index: 337729 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.5638. Min Act: -0.0000

Data Index: 518323 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.5417. Min Act: -0.0000

Data Index: 483429 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1153077 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.4915. Min Act: -0.0000

Data Index: 598256 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.4656. Min Act: -0.0000

Data Index: 551655 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.3547. Min Act: -0.0000

Data Index: 1182528 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.4243. Min Act: -0.0000

Data Index: 417145 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 2.2740. Min Range: -2.2740

Max Act: 1.3623. Min Act: -0.0000

Data Index: 351152 (C4 (Web Text))

Max Activating Token Index: 74