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

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

Neuron 759 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.7909. Min Act: -0.0000

Data Index: 268148 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.7174. Min Act: -0.0000

Data Index: 531373 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.5284. Min Act: -0.0000

Data Index: 885158 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.6481. Min Act: -0.0000

Data Index: 705382 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.3570. Min Act: -0.0000

Data Index: 1064014 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.0419. Min Act: -0.0000

Data Index: 605250 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.2665. Min Act: -0.0000

Data Index: 194506 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.3431. Min Act: -0.0000

Data Index: 1113302 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 2.7909. Min Range: -2.7909

Max Act: 1.9790. Min Act: -0.0000

Data Index: 426871 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.1050. Min Act: -0.0000

Data Index: 845042 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.1616. Min Act: -0.0000

Data Index: 1004860 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 2.7909. Min Range: -2.7909

Max Act: 1.8615. Min Act: -0.0000

Data Index: 129281 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 2.7909. Min Range: -2.7909

Max Act: 1.9538. Min Act: -0.0000

Data Index: 822161 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 2.7909. Min Range: -2.7909

Max Act: 1.9563. Min Act: -0.0000

Data Index: 1208317 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 2.7909. Min Range: -2.7909

Max Act: 2.1271. Min Act: -0.0000

Data Index: 427996 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 2.7909. Min Range: -2.7909

Max Act: 1.7720. Min Act: -0.0000

Data Index: 652745 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 2.7909. Min Range: -2.7909

Max Act: 1.8588. Min Act: -0.0000

Data Index: 423254 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 2.7909. Min Range: -2.7909

Max Act: 1.8189. Min Act: -0.0000

Data Index: 1034761 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 2.7909. Min Range: -2.7909

Max Act: 1.7162. Min Act: -0.0000

Data Index: 256428 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 2.7909. Min Range: -2.7909

Max Act: 1.7790. Min Act: -0.0000

Data Index: 656642 (C4 (Web Text))

Max Activating Token Index: 22