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

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

Neuron 1243 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.9269. Min Act: -0.0000

Data Index: 42756 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.8681. Min Act: -0.0000

Data Index: 855193 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.8461. Min Act: 0.0001

Data Index: 1305928 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.8181. Min Act: -0.0000

Data Index: 803006 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.7967. Min Act: -0.0000

Data Index: 385031 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.7844. Min Act: -0.0000

Data Index: 354124 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.7463. Min Act: 0.0000

Data Index: 281093 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.7559. Min Act: -0.0000

Data Index: 904891 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6638. Min Act: 0.0000

Data Index: 428036 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6997. Min Act: -0.0000

Data Index: 280639 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6901. Min Act: -0.0000

Data Index: 942778 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6395. Min Act: -0.0000

Data Index: 21991 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6340. Min Act: -0.0000

Data Index: 349708 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6346. Min Act: -0.0000

Data Index: 944608 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1167479 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6245. Min Act: -0.0000

Data Index: 173122 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1284653 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.5634. Min Act: -0.0000

Data Index: 846743 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.5930. Min Act: -0.0000

Data Index: 7256 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.9269. Min Range: -0.9269

Max Act: 0.5933. Min Act: -0.0000

Data Index: 607946 (C4 (Web Text))

Max Activating Token Index: 865