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

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

Neuron 6143 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0399. Min Range: -6.0399

Max Act: 6.0399. Min Act: -0.0000

Data Index: 1330877 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.7915. Min Act: -0.0000

Data Index: 516522 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.7294. Min Act: -0.0000

Data Index: 596304 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.7842. Min Act: -0.0000

Data Index: 1289337 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.7223. Min Act: -0.0000

Data Index: 183484 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.8761. Min Act: -0.0000

Data Index: 1306432 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.3570. Min Act: -0.0000

Data Index: 618729 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.4320. Min Act: -0.0000

Data Index: 280309 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.4066. Min Act: -0.0000

Data Index: 202765 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.4153. Min Act: -0.0000

Data Index: 1066763 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.3441. Min Act: -0.0000

Data Index: 85766 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.1053. Min Act: -0.0000

Data Index: 177098 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.0794. Min Act: -0.0000

Data Index: 248768 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 6.0399. Min Range: -6.0399

Max Act: 4.9414. Min Act: -0.0000

Data Index: 602286 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.0304. Min Act: -0.0000

Data Index: 632629 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.2007. Min Act: -0.0000

Data Index: 1078362 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 6.0399. Min Range: -6.0399

Max Act: 5.0076. Min Act: -0.0000

Data Index: 272756 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 6.0399. Min Range: -6.0399

Max Act: 4.8027. Min Act: -0.0000

Data Index: 885891 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 6.0399. Min Range: -6.0399

Max Act: 4.9779. Min Act: -0.0000

Data Index: 1066406 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 6.0399. Min Range: -6.0399

Max Act: 4.9511. Min Act: -0.0000

Data Index: 58757 (C4 (Web Text))

Max Activating Token Index: 984