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

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

Neuron 4671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.2184. Min Act: -0.0001

Data Index: 1269857 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.1743. Min Act: -0.0001

Data Index: 771604 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.5917. Min Act: -0.0001

Data Index: 632345 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.5354. Min Act: -0.0001

Data Index: 670158 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.7749. Min Act: -0.0001

Data Index: 982531 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.5807. Min Act: -0.0001

Data Index: 468962 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.3632. Min Act: -0.0001

Data Index: 108361 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.3680. Min Act: -0.0001

Data Index: 1354938 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.3805. Min Act: -0.0001

Data Index: 1090672 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.3520. Min Act: -0.0001

Data Index: 1280477 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.1907. Min Act: -0.0001

Data Index: 474793 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.1745. Min Act: -0.0001

Data Index: 783170 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.4589. Min Act: -0.0001

Data Index: 709563 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.2156. Min Act: -0.0001

Data Index: 141551 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.2573. Min Act: -0.0001

Data Index: 598561 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.2225. Min Act: -0.0001

Data Index: 710411 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.0859. Min Act: -0.0001

Data Index: 974725 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.2049. Min Act: -0.0001

Data Index: 1078998 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.0671. Min Act: -0.0001

Data Index: 846299 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 3.7749. Min Range: -3.7749

Max Act: 3.3674. Min Act: -0.0001

Data Index: 36098 (C4 (Web Text))

Max Activating Token Index: 163