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

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

Neuron 4743 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.8740. Min Act: -0.0000

Data Index: 433369 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.8119. Min Act: -0.0000

Data Index: 689975 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1127569 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7091. Min Act: -0.0000

Data Index: 170791 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6204. Min Act: -0.0000

Data Index: 614708 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5955. Min Act: -0.0000

Data Index: 186779 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6551. Min Act: -0.0000

Data Index: 810550 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6355. Min Act: -0.0000

Data Index: 692092 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6519. Min Act: -0.0000

Data Index: 320056 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6349. Min Act: -0.0000

Data Index: 565083 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5977. Min Act: -0.0000

Data Index: 980966 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6562. Min Act: -0.0000

Data Index: 963181 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1283700 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5836. Min Act: -0.0000

Data Index: 778025 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6181. Min Act: -0.0000

Data Index: 546249 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5554. Min Act: -0.0000

Data Index: 415976 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5734. Min Act: -0.0000

Data Index: 585554 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5817. Min Act: -0.0000

Data Index: 655695 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5827. Min Act: -0.0000

Data Index: 495057 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5199. Min Act: -0.0000

Data Index: 432369 (C4 (Web Text))

Max Activating Token Index: 241