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

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

Neuron 3067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.5468. Min Act: -0.0001

Data Index: 73135 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.4905. Min Act: -0.0001

Data Index: 550610 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.2551. Min Act: -0.0001

Data Index: 950689 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.2623. Min Act: -0.0001

Data Index: 396134 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.3855. Min Act: -0.0001

Data Index: 141964 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.3971. Min Act: -0.0001

Data Index: 872402 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.0140. Min Act: -0.0001

Data Index: 749180 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.1340. Min Act: -0.0001

Data Index: 623780 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.0635. Min Act: -0.0001

Data Index: 496610 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 3.5468. Min Range: -3.5468

Max Act: 2.9530. Min Act: -0.0001

Data Index: 968708 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.2263. Min Act: -0.0001

Data Index: 608904 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 3.5468. Min Range: -3.5468

Max Act: 2.9045. Min Act: -0.0001

Data Index: 1190029 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 3.5468. Min Range: -3.5468

Max Act: 2.8345. Min Act: -0.0001

Data Index: 533363 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 3.5468. Min Range: -3.5468

Max Act: 2.9729. Min Act: -0.0001

Data Index: 333226 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 3.5468. Min Range: -3.5468

Max Act: 2.7894. Min Act: -0.0001

Data Index: 692675 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 3.5468. Min Range: -3.5468

Max Act: 2.8971. Min Act: -0.0001

Data Index: 1246772 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 3.5468. Min Range: -3.5468

Max Act: 2.9300. Min Act: -0.0001

Data Index: 548725 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 3.5468. Min Range: -3.5468

Max Act: 2.8780. Min Act: -0.0001

Data Index: 125351 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 3.5468. Min Range: -3.5468

Max Act: 3.0150. Min Act: -0.0001

Data Index: 1251668 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 3.5468. Min Range: -3.5468

Max Act: 2.7381. Min Act: -0.0001

Data Index: 1288719 (C4 (Web Text))

Max Activating Token Index: 788