Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2018 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0633. Min Range: -2.0633

Max Act: 2.0633. Min Act: -0.0000

Data Index: 889647 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.9618. Min Act: -0.0000

Data Index: 250764 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.5194. Min Act: -0.0000

Data Index: 332853 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4287. Min Act: -0.0001

Data Index: 571029 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.5566. Min Act: -0.0000

Data Index: 672954 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.5397. Min Act: -0.0000

Data Index: 1343481 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.5573. Min Act: -0.0000

Data Index: 332788 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.5344. Min Act: -0.0000

Data Index: 554528 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4833. Min Act: -0.0000

Data Index: 27204 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.3640. Min Act: -0.0001

Data Index: 305747 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4738. Min Act: -0.0001

Data Index: 467636 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.3599. Min Act: -0.0000

Data Index: 460576 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.2772. Min Act: -0.0001

Data Index: 663978 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.3581. Min Act: -0.0000

Data Index: 795878 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4262. Min Act: -0.0000

Data Index: 222595 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.3801. Min Act: -0.0001

Data Index: 694950 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4145. Min Act: -0.0001

Data Index: 980754 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.4309. Min Act: -0.0000

Data Index: 946288 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.1951. Min Act: -0.0000

Data Index: 682600 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 2.0633. Min Range: -2.0633

Max Act: 1.2956. Min Act: -0.0001

Data Index: 1036448 (C4 (Web Text))

Max Activating Token Index: 532