Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1433 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0002

Data Index: 484289 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0564. Min Act: -0.0001

Data Index: 720556 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0570. Min Act: -0.0000

Data Index: 174711 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1083944 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1128055 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1185665 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0486. Min Act: -0.0002

Data Index: 759861 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1115208 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0491. Min Act: 0.0000

Data Index: 1055257 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0478. Min Act: -0.0002

Data Index: 243956 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0486. Min Act: -0.0001

Data Index: 816195 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0485. Min Act: -0.0002

Data Index: 101367 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0485. Min Act: -0.0000

Data Index: 202680 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0484. Min Act: -0.0001

Data Index: 800377 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0484. Min Act: -0.0002

Data Index: 14962 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0481. Min Act: -0.0002

Data Index: 303160 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0479. Min Act: 0.0000

Data Index: 483656 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0476. Min Act: -0.0002

Data Index: 491861 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0479. Min Act: -0.0002

Data Index: 308818 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0481. Min Act: -0.0001

Data Index: 299157 (C4 (Web Text))

Max Activating Token Index: 62