Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3619 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5799. Min Range: -2.5799

Max Act: 2.4754. Min Act: -0.0000

Data Index: 894650 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 2.5799. Min Range: -2.5799

Max Act: 2.3096. Min Act: -0.0001

Data Index: 203336 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 2.5799. Min Range: -2.5799

Max Act: 2.5799. Min Act: -0.0000

Data Index: 188339 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 2.5799. Min Range: -2.5799

Max Act: 2.2614. Min Act: -0.0001

Data Index: 1138040 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 2.5799. Min Range: -2.5799

Max Act: 2.2149. Min Act: -0.0001

Data Index: 364108 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.9965. Min Act: -0.0000

Data Index: 402728 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 2.5799. Min Range: -2.5799

Max Act: 2.0517. Min Act: -0.0001

Data Index: 1113521 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 2.5799. Min Range: -2.5799

Max Act: 2.0341. Min Act: -0.0000

Data Index: 560584 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.9974. Min Act: -0.0000

Data Index: 1152952 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.8843. Min Act: -0.0001

Data Index: 998042 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.7539. Min Act: -0.0001

Data Index: 592330 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.9337. Min Act: -0.0001

Data Index: 1123186 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.7312. Min Act: -0.0000

Data Index: 512669 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.7901. Min Act: -0.0000

Data Index: 334276 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.7627. Min Act: -0.0000

Data Index: 1289742 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.8970. Min Act: -0.0000

Data Index: 831610 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.8122. Min Act: -0.0000

Data Index: 689092 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.7678. Min Act: -0.0001

Data Index: 759357 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.7814. Min Act: -0.0000

Data Index: 1016644 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 2.5799. Min Range: -2.5799

Max Act: 1.6882. Min Act: -0.0001

Data Index: 295220 (C4 (Web Text))

Max Activating Token Index: 344