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

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

Neuron 1164 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: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0003

Data Index: 379562 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0694. Min Act: -0.0003

Data Index: 757848 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1212097 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0640. Min Act: -0.0003

Data Index: 318498 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0551. Min Act: -0.0003

Data Index: 640808 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0587. Min Act: -0.0003

Data Index: 243877 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0585. Min Act: -0.0003

Data Index: 760943 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0568. Min Act: -0.0003

Data Index: 412381 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0584. Min Act: -0.0003

Data Index: 435745 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0567. Min Act: -0.0003

Data Index: 420233 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0539. Min Act: -0.0003

Data Index: 725284 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1031656 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0537. Min Act: -0.0003

Data Index: 599487 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0542. Min Act: -0.0003

Data Index: 609996 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0522. Min Act: -0.0003

Data Index: 76249 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0511. Min Act: -0.0003

Data Index: 422262 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1012265 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0481. Min Act: -0.0003

Data Index: 103795 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0518. Min Act: -0.0003

Data Index: 305605 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0509. Min Act: -0.0003

Data Index: 837003 (C4 (Web Text))

Max Activating Token Index: 266