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

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

Neuron 2526 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: 0.0573. Min Range: -0.0573

Max Act: 0.0573. Min Act: -0.0003

Data Index: 39635 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0546. Min Act: -0.0003

Data Index: 1604022 (Python Code)

Max Activating Token Index: 753

Text #2

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1167464 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1230370 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0473. Min Act: -0.0003

Data Index: 37284 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0487. Min Act: -0.0003

Data Index: 228069 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0489. Min Act: -0.0003

Data Index: 934427 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1391078 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0417. Min Act: -0.0003

Data Index: 751638 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0454. Min Act: -0.0003

Data Index: 556933 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1165855 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0442. Min Act: -0.0003

Data Index: 483807 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0459. Min Act: -0.0003

Data Index: 755827 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0430. Min Act: -0.0003

Data Index: 877008 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1394849 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1591628 (Python Code)

Max Activating Token Index: 950

Text #16

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1608189 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0390. Min Act: -0.0003

Data Index: 800505 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1106550 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1120637 (C4 (Web Text))

Max Activating Token Index: 711