Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.9762. Min Act: -0.0000

Data Index: 939384 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.8683. Min Act: -0.0000

Data Index: 1019078 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.8885. Min Act: -0.0000

Data Index: 227383 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.8695. Min Act: -0.0000

Data Index: 624361 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.8134. Min Act: -0.0000

Data Index: 730145 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.6049. Min Act: -0.0000

Data Index: 87904 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.6136. Min Act: -0.0000

Data Index: 1339058 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.5749. Min Act: -0.0000

Data Index: 1528311 (Python Code)

Max Activating Token Index: 606

Text #8

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.2120. Min Act: -0.0000

Data Index: 57657 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.0807. Min Act: -0.0000

Data Index: 1063227 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.2930. Min Act: -0.0000

Data Index: 364071 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.1775. Min Act: -0.0000

Data Index: 224594 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.1161. Min Act: -0.0000

Data Index: 705325 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.2195. Min Act: -0.0000

Data Index: 1030511 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.0769. Min Act: -0.0000

Data Index: 641313 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.0745. Min Act: -0.0000

Data Index: 1215010 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 11.9762. Min Range: -11.9762

Max Act: 11.0364. Min Act: -0.0000

Data Index: 908327 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 11.9762. Min Range: -11.9762

Max Act: 10.9558. Min Act: -0.0000

Data Index: 413288 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 11.9762. Min Range: -11.9762

Max Act: 10.8185. Min Act: -0.0000

Data Index: 2849 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 11.9762. Min Range: -11.9762

Max Act: 10.8959. Min Act: -0.0000

Data Index: 1099521 (C4 (Web Text))

Max Activating Token Index: 733