Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5088 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.6294. Min Act: -0.0000

Data Index: 1234066 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.7216. Min Act: -0.0000

Data Index: 1298524 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5675. Min Act: -0.0000

Data Index: 491696 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4621. Min Act: -0.0000

Data Index: 95295 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4663. Min Act: -0.0000

Data Index: 881649 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4486. Min Act: -0.0000

Data Index: 1339597 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5288. Min Act: -0.0000

Data Index: 253227 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4283. Min Act: -0.0000

Data Index: 909439 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4673. Min Act: -0.0000

Data Index: 438594 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.3803. Min Act: -0.0000

Data Index: 1126519 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4620. Min Act: -0.0000

Data Index: 1435194 (Python Code)

Max Activating Token Index: 399

Text #11

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4599. Min Act: -0.0000

Data Index: 1290597 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4473. Min Act: -0.0000

Data Index: 364673 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.5248. Min Act: -0.0000

Data Index: 1108164 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.4292. Min Act: -0.0000

Data Index: 480090 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.3934. Min Act: -0.0000

Data Index: 1641817 (Python Code)

Max Activating Token Index: 306

Text #16

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.3038. Min Act: -0.0000

Data Index: 968533 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.3689. Min Act: -0.0000

Data Index: 257944 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1164122 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 1.7216. Min Range: -1.7216

Max Act: 1.3375. Min Act: -0.0000

Data Index: 228929 (C4 (Web Text))

Max Activating Token Index: 317