Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1076 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0575. Min Act: -0.0006

Data Index: 1310691 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0553. Min Act: -0.0006

Data Index: 1186293 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0548. Min Act: -0.0006

Data Index: 1051140 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0542. Min Act: -0.0006

Data Index: 1165915 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0532. Min Act: -0.0006

Data Index: 749288 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0519. Min Act: -0.0006

Data Index: 20476 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0520. Min Act: -0.0006

Data Index: 204586 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0520. Min Act: -0.0006

Data Index: 1196279 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0531. Min Act: -0.0006

Data Index: 531349 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0502. Min Act: -0.0006

Data Index: 138931 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0512. Min Act: -0.0006

Data Index: 197019 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0504. Min Act: -0.0006

Data Index: 848007 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0529. Min Act: -0.0006

Data Index: 438204 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0503. Min Act: -0.0006

Data Index: 1185905 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0502. Min Act: -0.0006

Data Index: 1067878 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0500. Min Act: -0.0005

Data Index: 44473 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0490. Min Act: -0.0006

Data Index: 1114844 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0487. Min Act: -0.0006

Data Index: 7136 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0495. Min Act: -0.0006

Data Index: 112055 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0485. Min Act: -0.0006

Data Index: 624179 (C4 (Web Text))

Max Activating Token Index: 702