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

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

Neuron 1832 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: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0003

Data Index: 248796 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0694. Min Act: -0.0003

Data Index: 709484 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0681. Min Act: -0.0003

Data Index: 801922 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0671. Min Act: -0.0003

Data Index: 335148 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0623. Min Act: -0.0004

Data Index: 526187 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0616. Min Act: -0.0003

Data Index: 205721 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0620. Min Act: -0.0003

Data Index: 77619 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0601. Min Act: -0.0004

Data Index: 361857 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0623. Min Act: -0.0004

Data Index: 187955 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0598. Min Act: -0.0004

Data Index: 261457 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1206326 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0599. Min Act: -0.0004

Data Index: 837507 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0591. Min Act: -0.0003

Data Index: 53690 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0570. Min Act: -0.0003

Data Index: 414946 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0568. Min Act: -0.0003

Data Index: 307648 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0572. Min Act: -0.0004

Data Index: 286997 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0559. Min Act: -0.0003

Data Index: 393974 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0566. Min Act: -0.0003

Data Index: 224388 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0552. Min Act: -0.0003

Data Index: 260790 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0572. Min Act: -0.0003

Data Index: 793694 (C4 (Web Text))

Max Activating Token Index: 490