Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 262 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.2739. Min Act: -0.0001

Data Index: 491926 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1834. Min Act: -0.0001

Data Index: 381651 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1567. Min Act: -0.0001

Data Index: 872593 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1051. Min Act: -0.0001

Data Index: 898750 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0018. Min Act: -0.0001

Data Index: 144732 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0771. Min Act: -0.0001

Data Index: 1318486 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0289. Min Act: -0.0001

Data Index: 1317931 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0719. Min Act: -0.0001

Data Index: 47795 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.8176. Min Act: -0.0001

Data Index: 34538 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9476. Min Act: -0.0001

Data Index: 1298173 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.7018. Min Act: -0.0001

Data Index: 579944 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0129. Min Act: -0.0001

Data Index: 807251 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9955. Min Act: -0.0001

Data Index: 776499 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9671. Min Act: -0.0001

Data Index: 1207755 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.8662. Min Act: -0.0001

Data Index: 573315 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9607. Min Act: -0.0001

Data Index: 1167578 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.8319. Min Act: -0.0001

Data Index: 1194870 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.8574. Min Act: -0.0001

Data Index: 283728 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.8679. Min Act: -0.0001

Data Index: 823536 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.7950. Min Act: -0.0001

Data Index: 1233539 (C4 (Web Text))

Max Activating Token Index: 264