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

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

Neuron 1688 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.2431. Min Act: -0.0000

Data Index: 490185 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.2367. Min Act: -0.0000

Data Index: 524981 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.2636. Min Act: -0.0001

Data Index: 1149842 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.1497. Min Act: -0.0000

Data Index: 239205 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.1411. Min Act: -0.0001

Data Index: 241920 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.1635. Min Act: -0.0000

Data Index: 1229582 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0318. Min Act: -0.0001

Data Index: 352408 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0673. Min Act: -0.0000

Data Index: 221369 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0542. Min Act: -0.0001

Data Index: 304023 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0769. Min Act: -0.0000

Data Index: 427953 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1043237 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9442. Min Act: -0.0001

Data Index: 1192140 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9825. Min Act: -0.0000

Data Index: 50575 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0457. Min Act: -0.0001

Data Index: 585013 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.8708. Min Act: -0.0000

Data Index: 856753 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0314. Min Act: -0.0001

Data Index: 523528 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1115974 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0044. Min Act: -0.0000

Data Index: 486498 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9933. Min Act: -0.0000

Data Index: 38731 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9363. Min Act: -0.0001

Data Index: 460246 (C4 (Web Text))

Max Activating Token Index: 487