Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3230 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.7533. Min Act: -0.0000

Data Index: 846767 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.2920. Min Act: -0.0000

Data Index: 1243894 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.8185. Min Act: -0.0001

Data Index: 312093 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.7309. Min Act: -0.0000

Data Index: 645980 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.7329. Min Act: -0.0000

Data Index: 17921 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.6905. Min Act: -0.0001

Data Index: 242403 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.7919. Min Act: -0.0000

Data Index: 378533 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.6248. Min Act: -0.0000

Data Index: 57902 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.5809. Min Act: -0.0001

Data Index: 1336645 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.5912. Min Act: -0.0001

Data Index: 717900 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.6578. Min Act: -0.0001

Data Index: 1358017 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.6620. Min Act: -0.0000

Data Index: 753575 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.4606. Min Act: -0.0000

Data Index: 938040 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.3112. Min Act: -0.0000

Data Index: 6757 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.6182. Min Act: -0.0000

Data Index: 930439 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.4256. Min Act: -0.0000

Data Index: 798465 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.2729. Min Act: -0.0000

Data Index: 528973 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.5849. Min Act: -0.0000

Data Index: 1080601 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.4202. Min Act: -0.0000

Data Index: 211202 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 4.7533. Min Range: -4.7533

Max Act: 3.2414. Min Act: -0.0000

Data Index: 1286691 (C4 (Web Text))

Max Activating Token Index: 926