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

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

Neuron 4281 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1539. Min Range: -4.1539

Max Act: 4.1539. Min Act: -0.0000

Data Index: 1318553 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 4.1539. Min Range: -4.1539

Max Act: 3.3257. Min Act: -0.0000

Data Index: 31255 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 4.1539. Min Range: -4.1539

Max Act: 3.0297. Min Act: -0.0000

Data Index: 285363 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.8275. Min Act: -0.0000

Data Index: 665518 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.6833. Min Act: -0.0000

Data Index: 705942 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.9870. Min Act: -0.0000

Data Index: 1221280 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.7757. Min Act: -0.0000

Data Index: 351251 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.7697. Min Act: -0.0000

Data Index: 1209561 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.6401. Min Act: -0.0000

Data Index: 1015492 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.6728. Min Act: -0.0000

Data Index: 1339182 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.4684. Min Act: -0.0000

Data Index: 498239 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.5960. Min Act: -0.0000

Data Index: 1021080 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.4604. Min Act: -0.0000

Data Index: 680846 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.4027. Min Act: -0.0000

Data Index: 488256 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.2305. Min Act: -0.0000

Data Index: 937963 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.5008. Min Act: -0.0000

Data Index: 1397277 (Python Code)

Max Activating Token Index: 793

Text #16

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.1753. Min Act: -0.0000

Data Index: 884047 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.4486. Min Act: -0.0000

Data Index: 490816 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.5787. Min Act: -0.0000

Data Index: 1034469 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 4.1539. Min Range: -4.1539

Max Act: 2.4041. Min Act: -0.0000

Data Index: 1200958 (C4 (Web Text))

Max Activating Token Index: 120