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

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

Neuron 989 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7549. Min Act: -0.0001

Data Index: 93364 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7067. Min Act: -0.0002

Data Index: 855149 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7886. Min Act: -0.0002

Data Index: 777153 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7528. Min Act: -0.0002

Data Index: 420801 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7241. Min Act: -0.0002

Data Index: 273640 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6960. Min Act: -0.0001

Data Index: 1242026 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7200. Min Act: -0.0001

Data Index: 664581 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7149. Min Act: -0.0002

Data Index: 588926 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7134. Min Act: -0.0002

Data Index: 772692 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6372. Min Act: -0.0002

Data Index: 625751 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6941. Min Act: -0.0001

Data Index: 358636 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7087. Min Act: -0.0001

Data Index: 1295177 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6498. Min Act: -0.0001

Data Index: 714029 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6280. Min Act: -0.0001

Data Index: 410948 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6894. Min Act: -0.0002

Data Index: 851674 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6876. Min Act: -0.0001

Data Index: 1357146 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6681. Min Act: -0.0002

Data Index: 993642 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6856. Min Act: -0.0001

Data Index: 1191190 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6945. Min Act: -0.0001

Data Index: 96754 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6217. Min Act: -0.0001

Data Index: 1404626 (Python Code)

Max Activating Token Index: 888