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

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

Neuron 1261 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0110. Min Range: -1.0110

Max Act: 1.0110. Min Act: -0.0001

Data Index: 1248704 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9202. Min Act: -0.0001

Data Index: 265097 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8768. Min Act: -0.0001

Data Index: 896232 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.9205. Min Act: -0.0001

Data Index: 691375 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8399. Min Act: -0.0001

Data Index: 45753 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1257962 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6609. Min Act: -0.0001

Data Index: 1628091 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6294. Min Act: -0.0001

Data Index: 365890 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6024. Min Act: -0.0000

Data Index: 527104 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.5988. Min Act: -0.0001

Data Index: 441283 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.5780. Min Act: -0.0001

Data Index: 1115168 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6067. Min Act: -0.0001

Data Index: 427193 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.5703. Min Act: -0.0001

Data Index: 1094807 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.5169. Min Act: -0.0001

Data Index: 1094450 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.5416. Min Act: -0.0001

Data Index: 1399855 (Python Code)

Max Activating Token Index: 357

Text #15

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.5576. Min Act: -0.0001

Data Index: 1640714 (Python Code)

Max Activating Token Index: 511

Text #16

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.5387. Min Act: -0.0001

Data Index: 1014024 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.5320. Min Act: -0.0001

Data Index: 866838 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.5390. Min Act: -0.0001

Data Index: 607102 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.5168. Min Act: -0.0001

Data Index: 763410 (C4 (Web Text))

Max Activating Token Index: 885