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

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

Neuron 4120 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: 0.5183. Min Range: -0.5183

Max Act: 0.5183. Min Act: -0.0000

Data Index: 111292 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.5153. Min Act: -0.0000

Data Index: 350915 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1210513 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4615. Min Act: -0.0000

Data Index: 812544 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4919. Min Act: -0.0000

Data Index: 737827 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4642. Min Act: -0.0000

Data Index: 961826 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.5035. Min Act: -0.0001

Data Index: 276886 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1066676 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4511. Min Act: -0.0000

Data Index: 764667 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4471. Min Act: -0.0000

Data Index: 671944 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4251. Min Act: -0.0000

Data Index: 304544 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4361. Min Act: -0.0000

Data Index: 317040 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4464. Min Act: -0.0000

Data Index: 81730 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4422. Min Act: -0.0000

Data Index: 116261 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4112. Min Act: -0.0000

Data Index: 825066 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1204706 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4107. Min Act: -0.0000

Data Index: 977024 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4021. Min Act: -0.0000

Data Index: 940880 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3923. Min Act: -0.0000

Data Index: 597976 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1243782 (C4 (Web Text))

Max Activating Token Index: 708