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

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

Neuron 4208 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6850. Min Range: -3.6850

Max Act: 3.6850. Min Act: -0.0000

Data Index: 313284 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 3.6850. Min Range: -3.6850

Max Act: 3.3215. Min Act: -0.0000

Data Index: 959067 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 3.6850. Min Range: -3.6850

Max Act: 3.1183. Min Act: -0.0000

Data Index: 403562 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.7655. Min Act: -0.0000

Data Index: 120408 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.5587. Min Act: -0.0000

Data Index: 72528 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.5436. Min Act: -0.0000

Data Index: 848844 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.6200. Min Act: -0.0000

Data Index: 373464 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.6682. Min Act: -0.0000

Data Index: 198358 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.6629. Min Act: -0.0000

Data Index: 429078 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.5189. Min Act: -0.0000

Data Index: 1250230 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.5018. Min Act: -0.0000

Data Index: 1392607 (Python Code)

Max Activating Token Index: 488

Text #11

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.4867. Min Act: -0.0000

Data Index: 240714 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.6221. Min Act: -0.0000

Data Index: 648080 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.4263. Min Act: -0.0000

Data Index: 490776 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.3637. Min Act: -0.0000

Data Index: 203971 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.3225. Min Act: -0.0000

Data Index: 127964 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.2849. Min Act: -0.0000

Data Index: 1117828 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.2699. Min Act: -0.0000

Data Index: 535095 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.2234. Min Act: -0.0000

Data Index: 914291 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 3.6850. Min Range: -3.6850

Max Act: 2.2165. Min Act: -0.0000

Data Index: 1023085 (C4 (Web Text))

Max Activating Token Index: 245