Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3160 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8574. Min Act: -0.0001

Data Index: 730639 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8504. Min Act: -0.0001

Data Index: 1009869 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7927. Min Act: -0.0001

Data Index: 29414 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7871. Min Act: -0.0001

Data Index: 285400 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7790. Min Act: -0.0001

Data Index: 409125 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8070. Min Act: -0.0002

Data Index: 272860 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8028. Min Act: -0.0001

Data Index: 77668 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8020. Min Act: -0.0001

Data Index: 615959 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7872. Min Act: -0.0001

Data Index: 314159 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7388. Min Act: -0.0002

Data Index: 767481 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7895. Min Act: -0.0001

Data Index: 900862 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8133. Min Act: -0.0002

Data Index: 1132946 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.8001. Min Act: -0.0002

Data Index: 452366 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.6521. Min Act: -0.0001

Data Index: 390528 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7681. Min Act: -0.0002

Data Index: 64375 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7515. Min Act: -0.0002

Data Index: 672224 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7356. Min Act: -0.0002

Data Index: 900523 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7313. Min Act: -0.0001

Data Index: 618656 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7453. Min Act: -0.0001

Data Index: 419215 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.8574. Min Range: -0.8574

Max Act: 0.7265. Min Act: -0.0002

Data Index: 855460 (C4 (Web Text))

Max Activating Token Index: 193