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

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

Neuron 3607 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.1015. Min Act: -0.0002

Data Index: 23786 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1268988 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1249412 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0619. Min Act: -0.0002

Data Index: 939369 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0657. Min Act: -0.0002

Data Index: 17209 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0697. Min Act: -0.0002

Data Index: 712617 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1330116 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0631. Min Act: -0.0002

Data Index: 339049 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0640. Min Act: -0.0002

Data Index: 667579 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0618. Min Act: -0.0002

Data Index: 274196 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1075772 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1296398 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1165398 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0585. Min Act: -0.0002

Data Index: 839169 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0597. Min Act: -0.0002

Data Index: 876243 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0617. Min Act: -0.0002

Data Index: 683091 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1170058 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0592. Min Act: -0.0002

Data Index: 374618 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0610. Min Act: -0.0002

Data Index: 330967 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0549. Min Act: -0.0002

Data Index: 571997 (C4 (Web Text))

Max Activating Token Index: 165