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

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

Neuron 423 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4862. Min Act: -0.0000

Data Index: 300985 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.5016. Min Act: -0.0000

Data Index: 923331 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4660. Min Act: -0.0000

Data Index: 611873 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4443. Min Act: -0.0000

Data Index: 607382 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4464. Min Act: -0.0000

Data Index: 536156 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4344. Min Act: -0.0001

Data Index: 1327173 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4330. Min Act: -0.0001

Data Index: 102351 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4590. Min Act: -0.0000

Data Index: 258042 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4437. Min Act: -0.0001

Data Index: 845308 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4579. Min Act: -0.0000

Data Index: 673173 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4411. Min Act: -0.0001

Data Index: 219904 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4078. Min Act: -0.0000

Data Index: 16149 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4455. Min Act: -0.0000

Data Index: 245865 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4389. Min Act: -0.0000

Data Index: 331637 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1231276 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1258894 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4184. Min Act: -0.0000

Data Index: 376485 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4162. Min Act: -0.0000

Data Index: 112520 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4024. Min Act: -0.0000

Data Index: 300677 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.5016. Min Range: -0.5016

Max Act: 0.4156. Min Act: -0.0000

Data Index: 729030 (C4 (Web Text))

Max Activating Token Index: 1006