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

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

Neuron 1200 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1121671 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4626. Min Act: -0.0000

Data Index: 951906 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.5417. Min Act: -0.0000

Data Index: 477681 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4915. Min Act: -0.0000

Data Index: 283014 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4709. Min Act: -0.0000

Data Index: 260950 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.5022. Min Act: -0.0000

Data Index: 428318 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4578. Min Act: -0.0000

Data Index: 227785 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4267. Min Act: -0.0000

Data Index: 197430 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4507. Min Act: -0.0000

Data Index: 683277 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4692. Min Act: -0.0000

Data Index: 939394 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4722. Min Act: -0.0000

Data Index: 370100 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4710. Min Act: -0.0000

Data Index: 563633 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1262881 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4778. Min Act: -0.0000

Data Index: 96109 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4066. Min Act: -0.0000

Data Index: 372577 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.4171. Min Act: -0.0000

Data Index: 690876 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3832. Min Act: -0.0000

Data Index: 212019 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1141439 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.2907. Min Act: -0.0000

Data Index: 86793 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.5701. Min Range: -0.5701

Max Act: 0.3289. Min Act: -0.0000

Data Index: 6246 (C4 (Web Text))

Max Activating Token Index: 115