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

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

Neuron 622 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: 1.8882. Min Range: -1.8882

Max Act: 1.8882. Min Act: -0.0000

Data Index: 1184292 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5730. Min Act: -0.0000

Data Index: 172734 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.6485. Min Act: -0.0000

Data Index: 359653 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5779. Min Act: -0.0000

Data Index: 1149685 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.5314. Min Act: -0.0000

Data Index: 201847 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1232635 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.2981. Min Act: -0.0000

Data Index: 119097 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3720. Min Act: -0.0000

Data Index: 12190 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3491. Min Act: -0.0000

Data Index: 519617 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3488. Min Act: -0.0000

Data Index: 968157 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3089. Min Act: -0.0000

Data Index: 541192 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3714. Min Act: -0.0000

Data Index: 1033409 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3539. Min Act: -0.0000

Data Index: 650875 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.2997. Min Act: -0.0000

Data Index: 19793 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1287983 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.1785. Min Act: -0.0000

Data Index: 264746 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.3277. Min Act: -0.0000

Data Index: 450842 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.2232. Min Act: -0.0000

Data Index: 160736 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.0938. Min Act: -0.0000

Data Index: 833164 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.8882. Min Range: -1.8882

Max Act: 1.2554. Min Act: -0.0000

Data Index: 359940 (C4 (Web Text))

Max Activating Token Index: 25