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

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

Neuron 2042 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0692. Min Range: -1.0692

Max Act: 1.0105. Min Act: -0.0002

Data Index: 204909 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.9620. Min Act: -0.0002

Data Index: 176140 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.9305. Min Act: -0.0002

Data Index: 966247 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7956. Min Act: -0.0002

Data Index: 699992 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.9826. Min Act: -0.0002

Data Index: 680678 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.9196. Min Act: -0.0002

Data Index: 126814 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 1.0692. Min Range: -1.0692

Max Act: 1.0692. Min Act: -0.0002

Data Index: 896211 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.8635. Min Act: -0.0002

Data Index: 316882 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.9146. Min Act: -0.0002

Data Index: 368861 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7181. Min Act: -0.0002

Data Index: 1293138 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 1.0692. Min Range: -1.0692

Max Act: 1.0144. Min Act: -0.0002

Data Index: 781610 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.8723. Min Act: -0.0002

Data Index: 1326253 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7848. Min Act: -0.0002

Data Index: 137302 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.9190. Min Act: -0.0002

Data Index: 408352 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.8550. Min Act: -0.0002

Data Index: 1023081 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.8547. Min Act: -0.0002

Data Index: 134378 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.8314. Min Act: -0.0002

Data Index: 333939 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.8750. Min Act: -0.0002

Data Index: 46840 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.9624. Min Act: -0.0002

Data Index: 1233930 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7136. Min Act: -0.0002

Data Index: 210484 (C4 (Web Text))

Max Activating Token Index: 284