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

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

Neuron 4829 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.5367. Min Act: -0.0000

Data Index: 899929 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.5287. Min Act: -0.0000

Data Index: 776079 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1128420 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1163208 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1188258 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4744. Min Act: -0.0000

Data Index: 705331 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1192550 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4432. Min Act: -0.0000

Data Index: 391568 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4354. Min Act: -0.0000

Data Index: 630323 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4464. Min Act: -0.0000

Data Index: 94791 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4544. Min Act: -0.0000

Data Index: 527622 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1297601 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4027. Min Act: -0.0000

Data Index: 835163 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4383. Min Act: -0.0000

Data Index: 842421 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1299339 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3794. Min Act: -0.0000

Data Index: 234422 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1026074 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1337017 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4081. Min Act: -0.0000

Data Index: 585531 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3784. Min Act: -0.0000

Data Index: 500655 (C4 (Web Text))

Max Activating Token Index: 453