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

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

Neuron 146 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5621. Min Act: -0.0000

Data Index: 555430 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5058. Min Act: -0.0000

Data Index: 796118 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.5178. Min Act: -0.0000

Data Index: 674600 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4985. Min Act: -0.0000

Data Index: 662799 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1157405 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4480. Min Act: -0.0000

Data Index: 64236 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1369909 (Python Code)

Max Activating Token Index: 750

Text #7

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1201313 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4693. Min Act: -0.0000

Data Index: 289821 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4358. Min Act: -0.0000

Data Index: 738044 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.3932. Min Act: -0.0000

Data Index: 166337 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4009. Min Act: -0.0000

Data Index: 77965 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4443. Min Act: -0.0000

Data Index: 755372 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1647725 (Python Code)

Max Activating Token Index: 156

Text #14

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1192771 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.3773. Min Act: -0.0000

Data Index: 137117 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1517480 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.4095. Min Act: -0.0000

Data Index: 303556 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1384833 (Python Code)

Max Activating Token Index: 83

Text #19

Max Range: 0.5621. Min Range: -0.5621

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1642648 (Python Code)

Max Activating Token Index: 165