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

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

Neuron 2275 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1245599 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4946. Min Act: -0.0000

Data Index: 493505 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4879. Min Act: -0.0000

Data Index: 869055 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1225827 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4152. Min Act: -0.0000

Data Index: 47235 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4584. Min Act: -0.0000

Data Index: 879938 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4036. Min Act: 0.0000

Data Index: 1088547 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1315664 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3811. Min Act: -0.0000

Data Index: 163730 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4201. Min Act: -0.0000

Data Index: 13578 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3915. Min Act: -0.0000

Data Index: 110208 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3880. Min Act: -0.0000

Data Index: 684650 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1245986 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3434. Min Act: -0.0000

Data Index: 959075 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1195279 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3626. Min Act: -0.0000

Data Index: 220552 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3493. Min Act: -0.0000

Data Index: 482370 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3465. Min Act: 0.0000

Data Index: 332748 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3354. Min Act: -0.0000

Data Index: 857911 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3520. Min Act: -0.0000

Data Index: 718500 (C4 (Web Text))

Max Activating Token Index: 294