Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4120 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.8401. Min Act: -0.0000

Data Index: 669715 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5948. Min Act: -0.0000

Data Index: 18824 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5849. Min Act: -0.0000

Data Index: 675699 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5970. Min Act: -0.0000

Data Index: 65425 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5656. Min Act: -0.0000

Data Index: 456479 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5510. Min Act: -0.0000

Data Index: 832964 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5441. Min Act: -0.0000

Data Index: 158614 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5145. Min Act: -0.0000

Data Index: 200299 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5465. Min Act: -0.0000

Data Index: 802029 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.4763. Min Act: -0.0000

Data Index: 684577 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5043. Min Act: -0.0000

Data Index: 595004 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.4696. Min Act: -0.0000

Data Index: 398673 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1191457 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.4742. Min Act: -0.0000

Data Index: 780862 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.4704. Min Act: -0.0000

Data Index: 787493 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.5157. Min Act: -0.0000

Data Index: 585676 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.4381. Min Act: -0.0000

Data Index: 554919 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.4630. Min Act: -0.0000

Data Index: 958790 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.4811. Min Act: -0.0000

Data Index: 206503 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.8401. Min Range: -0.8401

Max Act: 0.4908. Min Act: -0.0000

Data Index: 664140 (C4 (Web Text))

Max Activating Token Index: 879