Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1290 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.8466. Min Act: -0.0002

Data Index: 742834 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7816. Min Act: -0.0002

Data Index: 780371 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7714. Min Act: -0.0002

Data Index: 348062 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7162. Min Act: -0.0002

Data Index: 365796 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7410. Min Act: -0.0002

Data Index: 408359 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7332. Min Act: -0.0002

Data Index: 493152 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6900. Min Act: -0.0002

Data Index: 588557 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7027. Min Act: -0.0002

Data Index: 831700 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6898. Min Act: -0.0002

Data Index: 951133 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6931. Min Act: -0.0002

Data Index: 989596 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7000. Min Act: -0.0002

Data Index: 336291 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6755. Min Act: -0.0002

Data Index: 497081 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.7001. Min Act: -0.0002

Data Index: 373836 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6778. Min Act: -0.0002

Data Index: 599007 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6745. Min Act: -0.0002

Data Index: 782960 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6681. Min Act: -0.0002

Data Index: 105052 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6622. Min Act: -0.0002

Data Index: 1178600 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6393. Min Act: -0.0003

Data Index: 617791 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6425. Min Act: -0.0002

Data Index: 89801 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6469. Min Act: -0.0002

Data Index: 272347 (C4 (Web Text))

Max Activating Token Index: 808