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

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

Neuron 3004 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.7696. Min Act: -0.0000

Data Index: 754360 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.8821. Min Act: -0.0000

Data Index: 1190330 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.1213. Min Act: -0.0000

Data Index: 705291 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.6678. Min Act: -0.0000

Data Index: 1009639 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.8851. Min Act: -0.0000

Data Index: 838198 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.8284. Min Act: -0.0000

Data Index: 958796 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.7370. Min Act: -0.0000

Data Index: 472852 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.8013. Min Act: -0.0000

Data Index: 379669 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.8778. Min Act: -0.0000

Data Index: 114807 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.6414. Min Act: -0.0000

Data Index: 584378 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.7488. Min Act: -0.0000

Data Index: 179873 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.5243. Min Act: -0.0000

Data Index: 1293751 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.8117. Min Act: -0.0000

Data Index: 1041337 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.7700. Min Act: -0.0000

Data Index: 1127323 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.6528. Min Act: -0.0000

Data Index: 336619 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.6689. Min Act: -0.0000

Data Index: 138766 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.3391. Min Act: -0.0000

Data Index: 916943 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.5353. Min Act: -0.0000

Data Index: 528836 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.6433. Min Act: -0.0000

Data Index: 1351432 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 2.7696. Min Range: -2.7696

Max Act: 1.7327. Min Act: -0.0000

Data Index: 1631240 (Python Code)

Max Activating Token Index: 725