Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1548 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7617. Min Act: -0.0003

Data Index: 692997 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7613. Min Act: -0.0003

Data Index: 849132 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7501. Min Act: -0.0003

Data Index: 1324127 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7302. Min Act: -0.0003

Data Index: 268914 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7361. Min Act: -0.0003

Data Index: 1030133 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7284. Min Act: -0.0003

Data Index: 16645 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.6900. Min Act: -0.0003

Data Index: 531258 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.6657. Min Act: -0.0003

Data Index: 1077017 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7100. Min Act: -0.0003

Data Index: 228096 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.6524. Min Act: -0.0003

Data Index: 656317 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7305. Min Act: -0.0003

Data Index: 1201029 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.6818. Min Act: -0.0003

Data Index: 1246500 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7027. Min Act: -0.0003

Data Index: 124950 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.6806. Min Act: -0.0003

Data Index: 921037 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7060. Min Act: -0.0003

Data Index: 238993 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7045. Min Act: -0.0003

Data Index: 2270 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.6888. Min Act: -0.0003

Data Index: 358843 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.6794. Min Act: -0.0003

Data Index: 1004694 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.6870. Min Act: -0.0003

Data Index: 110618 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.6964. Min Act: -0.0003

Data Index: 502591 (C4 (Web Text))

Max Activating Token Index: 186