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

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

Neuron 2982 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: 1.9673. Min Range: -1.9673

Max Act: 1.9673. Min Act: -0.0002

Data Index: 415893 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.7326. Min Act: -0.0002

Data Index: 571797 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.7211. Min Act: -0.0003

Data Index: 337819 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.7734. Min Act: -0.0002

Data Index: 1244280 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.6859. Min Act: -0.0002

Data Index: 641337 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.6630. Min Act: -0.0002

Data Index: 1356320 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.6716. Min Act: -0.0002

Data Index: 129854 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.6213. Min Act: -0.0002

Data Index: 419483 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.6351. Min Act: -0.0002

Data Index: 589136 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.6258. Min Act: -0.0002

Data Index: 226851 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.6492. Min Act: -0.0002

Data Index: 1253604 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.6127. Min Act: -0.0003

Data Index: 919973 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.5788. Min Act: -0.0002

Data Index: 134129 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.5627. Min Act: -0.0002

Data Index: 607291 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.5447. Min Act: -0.0002

Data Index: 119639 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.5650. Min Act: -0.0002

Data Index: 973495 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.5412. Min Act: -0.0002

Data Index: 925463 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.5552. Min Act: -0.0002

Data Index: 496009 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.5366. Min Act: -0.0002

Data Index: 1055212 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 1.9673. Min Range: -1.9673

Max Act: 1.5160. Min Act: -0.0002

Data Index: 633056 (C4 (Web Text))

Max Activating Token Index: 398