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

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

Neuron 3481 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.5426. Min Act: -0.0000

Data Index: 878655 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.5029. Min Act: -0.0000

Data Index: 1255011 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.3961. Min Act: -0.0000

Data Index: 309375 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.3924. Min Act: -0.0000

Data Index: 857865 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.3897. Min Act: -0.0000

Data Index: 901922 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1078. Min Act: -0.0000

Data Index: 1270137 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1660. Min Act: -0.0000

Data Index: 385120 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1600. Min Act: -0.0000

Data Index: 610116 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1906. Min Act: -0.0000

Data Index: 40879 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.1906. Min Act: -0.0000

Data Index: 213017 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0944. Min Act: -0.0000

Data Index: 268895 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0337. Min Act: 0.0000

Data Index: 1381528 (Python Code)

Max Activating Token Index: 203

Text #12

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0492. Min Act: -0.0000

Data Index: 776306 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0176. Min Act: -0.0000

Data Index: 755403 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1209074 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0041. Min Act: -0.0000

Data Index: 722044 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0393. Min Act: 0.0000

Data Index: 574067 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0287. Min Act: 0.0002

Data Index: 1223770 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 1.5426. Min Range: -1.5426

Max Act: 1.0136. Min Act: -0.0000

Data Index: 246931 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 1.5426. Min Range: -1.5426

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1202034 (C4 (Web Text))

Max Activating Token Index: 923