Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1010 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.8514. Min Range: -3.8514

Max Act: 3.8514. Min Act: -0.0001

Data Index: 562427 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 3.8514. Min Range: -3.8514

Max Act: 2.8472. Min Act: -0.0000

Data Index: 778948 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 3.8514. Min Range: -3.8514

Max Act: 2.6053. Min Act: -0.0000

Data Index: 531250 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 3.8514. Min Range: -3.8514

Max Act: 2.0773. Min Act: -0.0001

Data Index: 320763 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.9630. Min Act: -0.0001

Data Index: 275748 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 3.8514. Min Range: -3.8514

Max Act: 2.3023. Min Act: -0.0000

Data Index: 774364 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 3.8514. Min Range: -3.8514

Max Act: 2.3314. Min Act: -0.0000

Data Index: 951589 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 3.8514. Min Range: -3.8514

Max Act: 2.0868. Min Act: -0.0000

Data Index: 1286725 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.9700. Min Act: -0.0000

Data Index: 789697 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.9490. Min Act: -0.0000

Data Index: 1095749 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.8575. Min Act: -0.0000

Data Index: 686576 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.8173. Min Act: -0.0000

Data Index: 491913 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 3.8514. Min Range: -3.8514

Max Act: 2.0232. Min Act: -0.0001

Data Index: 190272 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.6788. Min Act: -0.0000

Data Index: 718337 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.7805. Min Act: -0.0001

Data Index: 386290 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.6266. Min Act: -0.0000

Data Index: 452685 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.7265. Min Act: -0.0000

Data Index: 1099007 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.5676. Min Act: -0.0001

Data Index: 363383 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.7047. Min Act: -0.0001

Data Index: 26323 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 3.8514. Min Range: -3.8514

Max Act: 1.6847. Min Act: -0.0001

Data Index: 803135 (C4 (Web Text))

Max Activating Token Index: 544