Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 455 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.6441. Min Act: -0.0002

Data Index: 1387226 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5337. Min Act: -0.0002

Data Index: 1413215 (Python Code)

Max Activating Token Index: 714

Text #2

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5115. Min Act: -0.0002

Data Index: 1406418 (Python Code)

Max Activating Token Index: 565

Text #3

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5214. Min Act: -0.0002

Data Index: 1388271 (Python Code)

Max Activating Token Index: 789

Text #4

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5268. Min Act: -0.0002

Data Index: 1562289 (Python Code)

Max Activating Token Index: 393

Text #5

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4801. Min Act: -0.0002

Data Index: 1537894 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4621. Min Act: -0.0002

Data Index: 1578434 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.5184. Min Act: -0.0002

Data Index: 1609207 (Python Code)

Max Activating Token Index: 625

Text #8

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4874. Min Act: -0.0002

Data Index: 1593964 (Python Code)

Max Activating Token Index: 361

Text #9

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4639. Min Act: -0.0002

Data Index: 1422681 (Python Code)

Max Activating Token Index: 423

Text #10

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4588. Min Act: -0.0002

Data Index: 1640174 (Python Code)

Max Activating Token Index: 750

Text #11

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4519. Min Act: -0.0002

Data Index: 1470307 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4569. Min Act: -0.0002

Data Index: 1551336 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4029. Min Act: -0.0002

Data Index: 1435144 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4586. Min Act: -0.0002

Data Index: 1361706 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.3674. Min Act: -0.0002

Data Index: 1569913 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.3870. Min Act: -0.0002

Data Index: 1623993 (Python Code)

Max Activating Token Index: 160

Text #17

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.3913. Min Act: -0.0002

Data Index: 1571157 (Python Code)

Max Activating Token Index: 673

Text #18

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4125. Min Act: -0.0002

Data Index: 1137086 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 1.6441. Min Range: -1.6441

Max Act: 1.4237. Min Act: -0.0002

Data Index: 1500896 (Python Code)

Max Activating Token Index: 120