Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 604 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0627. Min Act: -0.0006

Data Index: 27110 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0600. Min Act: -0.0006

Data Index: 208385 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0604. Min Act: -0.0006

Data Index: 1056096 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0574. Min Act: -0.0006

Data Index: 565868 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0593. Min Act: -0.0006

Data Index: 1066782 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0591. Min Act: -0.0006

Data Index: 983420 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0613. Min Act: -0.0006

Data Index: 1168611 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0504. Min Act: -0.0006

Data Index: 677455 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0533. Min Act: -0.0006

Data Index: 1343711 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0540. Min Act: -0.0006

Data Index: 889714 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0563. Min Act: -0.0006

Data Index: 1179480 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0571. Min Act: -0.0006

Data Index: 701621 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0545. Min Act: -0.0006

Data Index: 762378 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0562. Min Act: -0.0006

Data Index: 482362 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0538. Min Act: -0.0006

Data Index: 1080445 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0559. Min Act: -0.0006

Data Index: 1030743 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0546. Min Act: -0.0006

Data Index: 713565 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0552. Min Act: -0.0006

Data Index: 158375 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0531. Min Act: -0.0006

Data Index: 734631 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0539. Min Act: -0.0006

Data Index: 116947 (C4 (Web Text))

Max Activating Token Index: 385