Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2189 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.3531. Min Act: -0.0001

Data Index: 421014 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.3662. Min Act: -0.0001

Data Index: 475140 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.3489. Min Act: -0.0001

Data Index: 734204 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.3245. Min Act: -0.0001

Data Index: 908181 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.3343. Min Act: -0.0001

Data Index: 57450 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2951. Min Act: -0.0001

Data Index: 171469 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2986. Min Act: -0.0001

Data Index: 710203 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2784. Min Act: -0.0001

Data Index: 499563 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2731. Min Act: -0.0001

Data Index: 189046 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2441. Min Act: -0.0001

Data Index: 37635 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2737. Min Act: -0.0001

Data Index: 544798 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2636. Min Act: -0.0001

Data Index: 348473 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2512. Min Act: -0.0001

Data Index: 704658 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2492. Min Act: -0.0001

Data Index: 327635 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2484. Min Act: -0.0001

Data Index: 779583 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2380. Min Act: 0.0001

Data Index: 794387 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2437. Min Act: -0.0001

Data Index: 406055 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2347. Min Act: -0.0001

Data Index: 990720 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2404. Min Act: -0.0001

Data Index: 7764 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.3662. Min Range: -0.3662

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1255334 (C4 (Web Text))

Max Activating Token Index: 149