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

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

Neuron 4168 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.4322. Min Act: -0.0001

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.3541. Min Act: -0.0001

Data Index: 1322405 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.3080. Min Act: -0.0001

Data Index: 1347728 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.3204. Min Act: -0.0001

Data Index: 661005 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.3185. Min Act: -0.0001

Data Index: 1114916 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2976. Min Act: -0.0001

Data Index: 31289 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2964. Min Act: -0.0001

Data Index: 16711 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2941. Min Act: -0.0001

Data Index: 587176 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2716. Min Act: -0.0001

Data Index: 43725 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1257570 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2784. Min Act: -0.0001

Data Index: 842625 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2502. Min Act: -0.0001

Data Index: 1086911 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1011011 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2587. Min Act: -0.0001

Data Index: 480401 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2512. Min Act: -0.0001

Data Index: 76187 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2503. Min Act: -0.0001

Data Index: 536808 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2671. Min Act: -0.0001

Data Index: 383764 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2376. Min Act: -0.0001

Data Index: 616354 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2429. Min Act: -0.0001

Data Index: 643904 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.4322. Min Range: -0.4322

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1340293 (C4 (Web Text))

Max Activating Token Index: 282