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

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

Neuron 189 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4434. Min Act: -0.0003

Data Index: 173569 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4292. Min Act: -0.0002

Data Index: 769716 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4085. Min Act: -0.0003

Data Index: 329082 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4027. Min Act: -0.0003

Data Index: 519342 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3919. Min Act: -0.0003

Data Index: 543722 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4026. Min Act: -0.0003

Data Index: 182873 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4134. Min Act: -0.0003

Data Index: 723072 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3727. Min Act: -0.0002

Data Index: 687142 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3800. Min Act: -0.0002

Data Index: 230653 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3788. Min Act: -0.0003

Data Index: 382756 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3904. Min Act: -0.0003

Data Index: 441830 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.4048. Min Act: -0.0002

Data Index: 744707 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3771. Min Act: -0.0002

Data Index: 236245 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3887. Min Act: -0.0003

Data Index: 938491 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3759. Min Act: -0.0003

Data Index: 1308464 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3872. Min Act: -0.0002

Data Index: 1039181 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3685. Min Act: -0.0002

Data Index: 355939 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3692. Min Act: -0.0003

Data Index: 855438 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3827. Min Act: -0.0002

Data Index: 509374 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3802. Min Act: -0.0003

Data Index: 442535 (C4 (Web Text))

Max Activating Token Index: 18