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

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

Neuron 133 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: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0003

Data Index: 899727 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1132794 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0817. Min Act: -0.0003

Data Index: 99054 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0825. Min Act: -0.0003

Data Index: 332191 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0760. Min Act: -0.0003

Data Index: 20851 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1238523 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0728. Min Act: -0.0003

Data Index: 236386 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0720. Min Act: -0.0003

Data Index: 932536 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0711. Min Act: -0.0003

Data Index: 52599 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1074057 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1310448 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0679. Min Act: -0.0003

Data Index: 1446057 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1628824 (Python Code)

Max Activating Token Index: 247

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1539815 (Python Code)

Max Activating Token Index: 488

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0691. Min Act: -0.0003

Data Index: 501307 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0693. Min Act: -0.0003

Data Index: 949576 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1296982 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0645. Min Act: -0.0003

Data Index: 780439 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1136176 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0665. Min Act: -0.0003

Data Index: 274858 (C4 (Web Text))

Max Activating Token Index: 425