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

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

Neuron 438 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0002

Data Index: 818121 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0643. Min Act: -0.0003

Data Index: 348334 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0607. Min Act: -0.0003

Data Index: 953925 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0602. Min Act: -0.0002

Data Index: 290974 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1208882 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0614. Min Act: -0.0002

Data Index: 507925 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0571. Min Act: -0.0002

Data Index: 661508 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0561. Min Act: -0.0002

Data Index: 876938 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0552. Min Act: -0.0003

Data Index: 783426 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1012891 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1169234 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1195365 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1088028 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0557. Min Act: -0.0003

Data Index: 198635 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0555. Min Act: -0.0003

Data Index: 497169 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1274269 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1150881 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1136941 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1001718 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1130509 (C4 (Web Text))

Max Activating Token Index: 812