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

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

Neuron 433 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: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0003

Data Index: 6782 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0597. Min Act: -0.0003

Data Index: 306448 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0532. Min Act: -0.0003

Data Index: 28865 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0507. Min Act: -0.0003

Data Index: 270040 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0523. Min Act: -0.0003

Data Index: 333086 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0529. Min Act: -0.0003

Data Index: 924455 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1216639 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1175292 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0484. Min Act: -0.0003

Data Index: 962502 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0473. Min Act: -0.0003

Data Index: 8822 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0508. Min Act: -0.0003

Data Index: 459956 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0524. Min Act: -0.0003

Data Index: 178999 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0498. Min Act: -0.0003

Data Index: 752930 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0508. Min Act: -0.0003

Data Index: 839352 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0513. Min Act: -0.0003

Data Index: 130943 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0477. Min Act: -0.0003

Data Index: 90455 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0486. Min Act: -0.0003

Data Index: 586278 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0479. Min Act: -0.0003

Data Index: 716360 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1191865 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0513. Min Act: -0.0003

Data Index: 955535 (C4 (Web Text))

Max Activating Token Index: 393