Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4702 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0800. Min Act: -0.0002

Data Index: 654069 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0818. Min Act: -0.0002

Data Index: 63317 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0769. Min Act: -0.0002

Data Index: 131490 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0755. Min Act: -0.0002

Data Index: 388411 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0738. Min Act: -0.0002

Data Index: 510658 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1240115 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0732. Min Act: -0.0002

Data Index: 185143 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1287930 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0716. Min Act: -0.0002

Data Index: 152853 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0706. Min Act: -0.0002

Data Index: 986141 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0681. Min Act: -0.0002

Data Index: 407341 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1312938 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0689. Min Act: -0.0002

Data Index: 770713 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1041452 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1245879 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0665. Min Act: -0.0002

Data Index: 855413 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0635. Min Act: -0.0002

Data Index: 541700 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0653. Min Act: -0.0002

Data Index: 591677 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0648. Min Act: -0.0002

Data Index: 387481 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0648. Min Act: -0.0002

Data Index: 729065 (C4 (Web Text))

Max Activating Token Index: 308