Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 979 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2486. Min Act: -0.0000

Data Index: 218750 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1927. Min Act: -0.0000

Data Index: 619054 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1863. Min Act: -0.0001

Data Index: 460217 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1856. Min Act: -0.0001

Data Index: 841243 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1910. Min Act: -0.0001

Data Index: 688158 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1847. Min Act: -0.0001

Data Index: 408639 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1896. Min Act: -0.0000

Data Index: 797345 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1873. Min Act: -0.0001

Data Index: 135250 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1132119 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1936. Min Act: -0.0000

Data Index: 351251 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1874. Min Act: -0.0001

Data Index: 675668 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1816. Min Act: -0.0001

Data Index: 984253 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1731. Min Act: -0.0001

Data Index: 897810 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1712. Min Act: -0.0000

Data Index: 924570 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1769. Min Act: -0.0000

Data Index: 301791 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1704. Min Act: -0.0000

Data Index: 176376 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1225431 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1726. Min Act: -0.0001

Data Index: 410513 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1714. Min Act: -0.0001

Data Index: 875417 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1213365 (C4 (Web Text))

Max Activating Token Index: 304