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

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

Neuron 3519 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: 0.5721. Min Range: -0.5721

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1240448 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.5429. Min Act: -0.0000

Data Index: 569772 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.5602. Min Act: -0.0000

Data Index: 512190 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.5411. Min Act: -0.0000

Data Index: 47318 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4952. Min Act: -0.0000

Data Index: 180516 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1014753 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4693. Min Act: -0.0000

Data Index: 299199 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4827. Min Act: -0.0000

Data Index: 268894 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4756. Min Act: -0.0000

Data Index: 494150 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4445. Min Act: -0.0000

Data Index: 685632 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1131585 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4386. Min Act: -0.0000

Data Index: 832755 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4289. Min Act: -0.0000

Data Index: 37132 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4161. Min Act: -0.0000

Data Index: 989176 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1573 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4354. Min Act: -0.0000

Data Index: 591664 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4344. Min Act: -0.0000

Data Index: 729091 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4200. Min Act: -0.0000

Data Index: 38423 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4127. Min Act: -0.0000

Data Index: 510284 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.5721. Min Range: -0.5721

Max Act: 0.4087. Min Act: -0.0000

Data Index: 522371 (C4 (Web Text))

Max Activating Token Index: 845