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

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

Neuron 451 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0793. Min Range: -2.0793

Max Act: 2.0737. Min Act: -0.0000

Data Index: 1330904 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 2.0793. Min Range: -2.0793

Max Act: 2.0793. Min Act: -0.0000

Data Index: 601872 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.7552. Min Act: -0.0001

Data Index: 87329 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6860. Min Act: -0.0000

Data Index: 113165 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6019. Min Act: -0.0000

Data Index: 636545 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6691. Min Act: -0.0001

Data Index: 1119374 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6485. Min Act: -0.0000

Data Index: 1115700 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5701. Min Act: -0.0000

Data Index: 394172 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6058. Min Act: -0.0000

Data Index: 884756 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6443. Min Act: -0.0000

Data Index: 615096 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6104. Min Act: -0.0000

Data Index: 634610 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.4028. Min Act: -0.0000

Data Index: 665685 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6792. Min Act: -0.0000

Data Index: 921821 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5719. Min Act: -0.0001

Data Index: 605063 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.4768. Min Act: -0.0001

Data Index: 1303760 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5552. Min Act: -0.0000

Data Index: 45361 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5333. Min Act: -0.0000

Data Index: 651693 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.4581. Min Act: -0.0000

Data Index: 497207 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5402. Min Act: -0.0001

Data Index: 742740 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5408. Min Act: -0.0000

Data Index: 90573 (C4 (Web Text))

Max Activating Token Index: 1020