Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1410 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0795. Min Act: -0.0004

Data Index: 855695 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0774. Min Act: -0.0003

Data Index: 1046539 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0761. Min Act: -0.0003

Data Index: 74531 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1447134 (Python Code)

Max Activating Token Index: 160

Text #4

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0677. Min Act: -0.0003

Data Index: 79470 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0698. Min Act: -0.0003

Data Index: 268870 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1121691 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1118429 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1379767 (Python Code)

Max Activating Token Index: 829

Text #9

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1398849 (Python Code)

Max Activating Token Index: 823

Text #10

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1474983 (Python Code)

Max Activating Token Index: 890

Text #11

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1258099 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0671. Min Act: -0.0003

Data Index: 98382 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0657. Min Act: -0.0003

Data Index: 1273167 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0680. Min Act: -0.0003

Data Index: 681775 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0656. Min Act: -0.0002

Data Index: 812768 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1182255 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0665. Min Act: -0.0003

Data Index: 639027 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1503812 (Python Code)

Max Activating Token Index: 293

Text #19

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0648. Min Act: -0.0003

Data Index: 319870 (C4 (Web Text))

Max Activating Token Index: 763