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

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

Neuron 661 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0979. Min Act: -0.0002

Data Index: 464413 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0895. Min Act: -0.0002

Data Index: 686543 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1106603 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1000192 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0919. Min Act: -0.0002

Data Index: 769078 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0835. Min Act: -0.0002

Data Index: 222025 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1593133 (Python Code)

Max Activating Token Index: 514

Text #7

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0851. Min Act: -0.0002

Data Index: 137350 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0810. Min Act: -0.0002

Data Index: 390636 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1209402 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1090469 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1160886 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1291528 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0767. Min Act: -0.0002

Data Index: 307346 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0784. Min Act: -0.0002

Data Index: 836793 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0756. Min Act: -0.0002

Data Index: 644425 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0800. Min Act: -0.0002

Data Index: 237676 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0769. Min Act: -0.0002

Data Index: 160406 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1095128 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1005847 (C4 (Web Text))

Max Activating Token Index: 619