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

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

Neuron 4077 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.7650. Min Act: -0.0000

Data Index: 682157 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.7148. Min Act: 0.0001

Data Index: 155513 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.6674. Min Act: -0.0000

Data Index: 789187 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.6359. Min Act: -0.0000

Data Index: 927893 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1259674 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1277146 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5596. Min Act: 0.0000

Data Index: 535317 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5344. Min Act: 0.0000

Data Index: 10424 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5357. Min Act: 0.0000

Data Index: 590222 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5277. Min Act: 0.0001

Data Index: 174966 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5045. Min Act: -0.0000

Data Index: 987434 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1181028 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5237. Min Act: -0.0000

Data Index: 452494 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4944. Min Act: -0.0000

Data Index: 710564 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4672. Min Act: -0.0000

Data Index: 35702 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1022028 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4472. Min Act: 0.0000

Data Index: 512255 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1346214 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4729. Min Act: -0.0000

Data Index: 941882 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.4541. Min Act: 0.0000

Data Index: 490827 (C4 (Web Text))

Max Activating Token Index: 899