Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1966 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.5898. Min Act: -0.0001

Data Index: 809935 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.5617. Min Act: -0.0001

Data Index: 786566 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.5653. Min Act: -0.0001

Data Index: 735893 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.5377. Min Act: -0.0001

Data Index: 202241 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.5174. Min Act: -0.0001

Data Index: 1242882 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4643. Min Act: -0.0001

Data Index: 1139441 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.5035. Min Act: -0.0001

Data Index: 716616 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4885. Min Act: -0.0001

Data Index: 517695 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4477. Min Act: -0.0001

Data Index: 165212 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4599. Min Act: -0.0001

Data Index: 702208 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4787. Min Act: -0.0001

Data Index: 1333901 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4886. Min Act: -0.0001

Data Index: 36480 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4582. Min Act: -0.0001

Data Index: 280363 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4530. Min Act: -0.0001

Data Index: 530764 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4762. Min Act: -0.0001

Data Index: 348858 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4512. Min Act: -0.0001

Data Index: 314288 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4380. Min Act: -0.0001

Data Index: 449599 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4516. Min Act: -0.0001

Data Index: 96834 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4467. Min Act: -0.0001

Data Index: 1250641 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4600. Min Act: -0.0001

Data Index: 615458 (C4 (Web Text))

Max Activating Token Index: 411