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

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

Neuron 4434 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5717. Min Act: -0.0000

Data Index: 971726 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.6000. Min Act: -0.0000

Data Index: 586333 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5521. Min Act: -0.0000

Data Index: 827892 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5585. Min Act: -0.0000

Data Index: 719729 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4217. Min Act: -0.0000

Data Index: 667805 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4174. Min Act: -0.0000

Data Index: 143366 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3743. Min Act: -0.0000

Data Index: 555484 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4234. Min Act: -0.0000

Data Index: 326542 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4227. Min Act: -0.0000

Data Index: 321244 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3970. Min Act: -0.0000

Data Index: 196016 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3842. Min Act: -0.0001

Data Index: 1127366 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4241. Min Act: -0.0000

Data Index: 853663 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3836. Min Act: -0.0001

Data Index: 429009 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1041060 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3873. Min Act: -0.0000

Data Index: 918343 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1033331 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3610. Min Act: -0.0000

Data Index: 360328 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3437. Min Act: -0.0000

Data Index: 5266 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3619. Min Act: -0.0000

Data Index: 43138 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3739. Min Act: -0.0000

Data Index: 195495 (C4 (Web Text))

Max Activating Token Index: 314