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

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

Neuron 3333 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0545. Min Range: -4.0545

Max Act: 4.0545. Min Act: -0.0000

Data Index: 1348582 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 4.0545. Min Range: -4.0545

Max Act: 3.8740. Min Act: -0.0000

Data Index: 821403 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 4.0545. Min Range: -4.0545

Max Act: 3.3913. Min Act: -0.0000

Data Index: 354742 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 4.0545. Min Range: -4.0545

Max Act: 3.1909. Min Act: -0.0000

Data Index: 869309 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 4.0545. Min Range: -4.0545

Max Act: 3.4589. Min Act: -0.0000

Data Index: 208669 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 4.0545. Min Range: -4.0545

Max Act: 3.1450. Min Act: -0.0000

Data Index: 581586 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.8812. Min Act: -0.0000

Data Index: 389182 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.6947. Min Act: -0.0000

Data Index: 679999 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 4.0545. Min Range: -4.0545

Max Act: 3.0301. Min Act: -0.0000

Data Index: 191608 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.7877. Min Act: -0.0000

Data Index: 453137 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.7691. Min Act: -0.0000

Data Index: 1313185 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.8863. Min Act: -0.0000

Data Index: 90198 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.6162. Min Act: -0.0000

Data Index: 630483 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.7059. Min Act: -0.0000

Data Index: 446895 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.5771. Min Act: -0.0000

Data Index: 1248133 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.6386. Min Act: -0.0000

Data Index: 819458 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.7448. Min Act: -0.0000

Data Index: 506224 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.5959. Min Act: -0.0000

Data Index: 463145 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.5020. Min Act: -0.0000

Data Index: 1169506 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 4.0545. Min Range: -4.0545

Max Act: 2.3595. Min Act: -0.0000

Data Index: 680397 (C4 (Web Text))

Max Activating Token Index: 101