Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 485 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1301231 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0686. Min Act: -0.0003

Data Index: 728506 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1137750 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0596. Min Act: -0.0003

Data Index: 987682 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0582. Min Act: -0.0003

Data Index: 576303 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0586. Min Act: -0.0003

Data Index: 29479 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0574. Min Act: -0.0003

Data Index: 921813 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0530. Min Act: -0.0003

Data Index: 606912 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0535. Min Act: -0.0003

Data Index: 607283 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1176436 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1096124 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0537. Min Act: -0.0003

Data Index: 76145 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0543. Min Act: -0.0003

Data Index: 524420 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0529. Min Act: -0.0003

Data Index: 692113 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0527. Min Act: -0.0003

Data Index: 506392 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0556. Min Act: -0.0003

Data Index: 869728 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0511. Min Act: -0.0003

Data Index: 830837 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0508. Min Act: -0.0003

Data Index: 240604 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0504. Min Act: -0.0003

Data Index: 258767 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0532. Min Act: -0.0003

Data Index: 28236 (C4 (Web Text))

Max Activating Token Index: 392