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

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

Neuron 1913 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: 0.6002. Min Range: -0.6002

Max Act: 0.6002. Min Act: -0.0000

Data Index: 68551 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5182. Min Act: -0.0000

Data Index: 743897 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1184825 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4827. Min Act: -0.0000

Data Index: 704050 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1228605 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4981. Min Act: -0.0000

Data Index: 755989 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4791. Min Act: -0.0000

Data Index: 134667 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4880. Min Act: -0.0000

Data Index: 579233 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1315697 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4664. Min Act: -0.0000

Data Index: 902055 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4523. Min Act: -0.0000

Data Index: 314358 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4665. Min Act: -0.0000

Data Index: 165638 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4501. Min Act: -0.0000

Data Index: 431057 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4344. Min Act: -0.0000

Data Index: 914661 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4181. Min Act: -0.0000

Data Index: 958510 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4286. Min Act: -0.0000

Data Index: 739766 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4485. Min Act: -0.0000

Data Index: 272858 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1036061 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4213. Min Act: -0.0000

Data Index: 787991 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4134. Min Act: -0.0000

Data Index: 555864 (C4 (Web Text))

Max Activating Token Index: 149