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

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

Neuron 2125 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1238900 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4511. Min Act: -0.0000

Data Index: 517963 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4498. Min Act: -0.0000

Data Index: 966617 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4212. Min Act: -0.0000

Data Index: 442186 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1130760 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4244. Min Act: -0.0000

Data Index: 391414 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3783. Min Act: -0.0000

Data Index: 999073 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3711. Min Act: -0.0000

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1188558 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3919. Min Act: -0.0000

Data Index: 516539 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3425. Min Act: -0.0000

Data Index: 908530 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3536. Min Act: -0.0000

Data Index: 170862 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3647. Min Act: -0.0000

Data Index: 243734 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3519. Min Act: -0.0000

Data Index: 108394 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3609. Min Act: -0.0000

Data Index: 231020 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1272783 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1254362 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3343. Min Act: -0.0000

Data Index: 128103 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3108. Min Act: -0.0000

Data Index: 746980 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3050. Min Act: -0.0000

Data Index: 609712 (C4 (Web Text))

Max Activating Token Index: 703