Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2444 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0524. Min Act: -0.0003

Data Index: 877713 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0505. Min Act: -0.0003

Data Index: 730120 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0469. Min Act: -0.0002

Data Index: 318051 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0458. Min Act: -0.0003

Data Index: 772622 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0453. Min Act: -0.0002

Data Index: 269129 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0444. Min Act: -0.0003

Data Index: 396432 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0433. Min Act: -0.0003

Data Index: 228828 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0426. Min Act: -0.0003

Data Index: 771738 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1246691 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0424. Min Act: -0.0003

Data Index: 234652 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1243076 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0416. Min Act: -0.0003

Data Index: 822203 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1232373 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0418. Min Act: -0.0002

Data Index: 526233 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1033834 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0404. Min Act: -0.0003

Data Index: 512652 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1353164 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0403. Min Act: -0.0002

Data Index: 313583 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1258050 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0385. Min Act: -0.0002

Data Index: 760557 (C4 (Web Text))

Max Activating Token Index: 970