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

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

Neuron 5715 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.8543. Min Act: -0.0000

Data Index: 815780 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.8515. Min Act: -0.0000

Data Index: 796011 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.1563. Min Act: -0.0000

Data Index: 1190570 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.9277. Min Act: -0.0000

Data Index: 801756 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.6837. Min Act: -0.0000

Data Index: 333512 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.6366. Min Act: -0.0000

Data Index: 225481 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.2949. Min Act: -0.0000

Data Index: 1065888 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.4041. Min Act: -0.0000

Data Index: 457432 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.5131. Min Act: -0.0000

Data Index: 84028 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.5623. Min Act: -0.0000

Data Index: 493344 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.3482. Min Act: -0.0000

Data Index: 984585 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.3135. Min Act: -0.0000

Data Index: 68329 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.1081. Min Act: -0.0000

Data Index: 1278040 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 4.8543. Min Range: -4.8543

Max Act: 2.8467. Min Act: -0.0000

Data Index: 1270112 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.1228. Min Act: -0.0000

Data Index: 1216019 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.3809. Min Act: -0.0000

Data Index: 238915 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.2115. Min Act: -0.0000

Data Index: 69615 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.1928. Min Act: -0.0000

Data Index: 605800 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.3223. Min Act: -0.0000

Data Index: 443549 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 4.8543. Min Range: -4.8543

Max Act: 3.1680. Min Act: -0.0000

Data Index: 826589 (C4 (Web Text))

Max Activating Token Index: 549