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

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

Neuron 73 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1349478 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3409. Min Act: -0.0000

Data Index: 579404 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1073208 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3103. Min Act: -0.0000

Data Index: 65922 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1064872 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2826. Min Act: -0.0000

Data Index: 972240 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3128. Min Act: -0.0000

Data Index: 34145 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3123. Min Act: -0.0000

Data Index: 437077 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2888. Min Act: -0.0000

Data Index: 379089 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2793. Min Act: -0.0000

Data Index: 124896 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2944. Min Act: -0.0000

Data Index: 847498 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1000644 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2713. Min Act: -0.0000

Data Index: 791342 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2827. Min Act: -0.0000

Data Index: 797541 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3671. Min Act: -0.0000

Data Index: 759007 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3209. Min Act: -0.0000

Data Index: 710874 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1033153 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2722. Min Act: -0.0000

Data Index: 450532 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2631. Min Act: -0.0000

Data Index: 16633 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2515. Min Act: -0.0000

Data Index: 96331 (C4 (Web Text))

Max Activating Token Index: 828