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

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

Neuron 122 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2657. Min Range: -4.2657

Max Act: 4.2657. Min Act: -0.0000

Data Index: 307609 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 4.2657. Min Range: -4.2657

Max Act: 3.7783. Min Act: -0.0000

Data Index: 584181 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 4.2657. Min Range: -4.2657

Max Act: 3.8874. Min Act: -0.0000

Data Index: 778292 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 4.2657. Min Range: -4.2657

Max Act: 3.1777. Min Act: -0.0000

Data Index: 299563 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 4.2657. Min Range: -4.2657

Max Act: 3.1150. Min Act: -0.0000

Data Index: 339885 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.6909. Min Act: -0.0000

Data Index: 330234 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.9570. Min Act: -0.0000

Data Index: 612407 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.9981. Min Act: -0.0000

Data Index: 525581 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.9444. Min Act: -0.0000

Data Index: 81020 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.9550. Min Act: -0.0000

Data Index: 686318 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.6479. Min Act: -0.0000

Data Index: 854925 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.7569. Min Act: -0.0000

Data Index: 712349 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.5493. Min Act: -0.0000

Data Index: 494285 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.3189. Min Act: -0.0000

Data Index: 238917 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.6081. Min Act: -0.0000

Data Index: 1038655 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.4669. Min Act: -0.0000

Data Index: 435052 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.5844. Min Act: -0.0000

Data Index: 175069 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.4023. Min Act: -0.0000

Data Index: 985785 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.4222. Min Act: -0.0000

Data Index: 296486 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 4.2657. Min Range: -4.2657

Max Act: 2.4607. Min Act: -0.0000

Data Index: 1321242 (C4 (Web Text))

Max Activating Token Index: 206