Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 806 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.4602. Min Act: -0.0001

Data Index: 36047 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.4378. Min Act: -0.0002

Data Index: 362313 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3921. Min Act: -0.0002

Data Index: 462422 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3783. Min Act: -0.0002

Data Index: 1170388 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3748. Min Act: -0.0001

Data Index: 26068 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3590. Min Act: -0.0002

Data Index: 305076 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3512. Min Act: -0.0002

Data Index: 819213 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3492. Min Act: -0.0002

Data Index: 246468 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3468. Min Act: -0.0002

Data Index: 1353058 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3527. Min Act: -0.0001

Data Index: 169020 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3506. Min Act: -0.0002

Data Index: 1237214 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3605. Min Act: -0.0002

Data Index: 255187 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3461. Min Act: -0.0001

Data Index: 837587 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3417. Min Act: -0.0002

Data Index: 1081906 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3512. Min Act: -0.0002

Data Index: 274117 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3424. Min Act: -0.0002

Data Index: 418524 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3502. Min Act: -0.0002

Data Index: 657972 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3404. Min Act: -0.0002

Data Index: 802931 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3332. Min Act: -0.0002

Data Index: 902242 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3382. Min Act: -0.0001

Data Index: 721067 (C4 (Web Text))

Max Activating Token Index: 618