Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4016 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.5335. Min Act: -0.0001

Data Index: 96169 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 2.5335. Min Range: -2.5335

Max Act: 2.0598. Min Act: -0.0001

Data Index: 421610 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.9404. Min Act: -0.0000

Data Index: 1272513 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.8688. Min Act: -0.0000

Data Index: 1201237 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.7853. Min Act: -0.0000

Data Index: 454762 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.6736. Min Act: -0.0000

Data Index: 653579 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.6424. Min Act: -0.0000

Data Index: 200045 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.6326. Min Act: -0.0000

Data Index: 72351 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.6277. Min Act: -0.0000

Data Index: 224756 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.6007. Min Act: -0.0001

Data Index: 1061407 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.5797. Min Act: -0.0001

Data Index: 787309 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.6555. Min Act: -0.0000

Data Index: 337446 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.6380. Min Act: -0.0000

Data Index: 265485 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.3713. Min Act: -0.0000

Data Index: 725532 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.5008. Min Act: -0.0000

Data Index: 1007161 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.4783. Min Act: -0.0000

Data Index: 861503 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.5108. Min Act: -0.0001

Data Index: 679310 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.4208. Min Act: -0.0000

Data Index: 540126 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1018544 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 2.5335. Min Range: -2.5335

Max Act: 1.3776. Min Act: -0.0001

Data Index: 290838 (C4 (Web Text))

Max Activating Token Index: 235