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

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

Neuron 732 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.7027. Min Act: -0.0000

Data Index: 349161 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1068002 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1089765 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4221. Min Act: -0.0000

Data Index: 952030 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5682. Min Act: -0.0000

Data Index: 146212 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4940. Min Act: -0.0000

Data Index: 990973 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5132. Min Act: -0.0000

Data Index: 808764 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1220499 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5205. Min Act: -0.0000

Data Index: 487826 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5142. Min Act: -0.0000

Data Index: 958654 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4456. Min Act: -0.0000

Data Index: 655079 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.5026. Min Act: -0.0000

Data Index: 599052 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4799. Min Act: -0.0000

Data Index: 883477 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4683. Min Act: 0.0001

Data Index: 1058009 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1335830 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4410. Min Act: -0.0000

Data Index: 631806 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1421699 (Python Code)

Max Activating Token Index: 417

Text #17

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4407. Min Act: -0.0000

Data Index: 328659 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4384. Min Act: -0.0000

Data Index: 470403 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.7027. Min Range: -0.7027

Max Act: 0.4194. Min Act: -0.0000

Data Index: 91887 (C4 (Web Text))

Max Activating Token Index: 807