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

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

Neuron 1921 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0004

Data Index: 1052786 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0544. Min Act: -0.0004

Data Index: 593752 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0526. Min Act: -0.0004

Data Index: 48837 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0522. Min Act: -0.0004

Data Index: 577823 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0485. Min Act: -0.0004

Data Index: 333913 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0413. Min Act: -0.0004

Data Index: 399051 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0471. Min Act: -0.0004

Data Index: 646751 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0434. Min Act: -0.0004

Data Index: 607689 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0452. Min Act: -0.0004

Data Index: 1357209 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0454. Min Act: -0.0004

Data Index: 938930 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0452. Min Act: -0.0004

Data Index: 82142 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0474. Min Act: -0.0004

Data Index: 392965 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0447. Min Act: -0.0004

Data Index: 1020380 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0427. Min Act: -0.0004

Data Index: 1625934 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0451. Min Act: -0.0004

Data Index: 909169 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0463. Min Act: -0.0004

Data Index: 1088280 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0445. Min Act: -0.0004

Data Index: 169231 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0443. Min Act: -0.0004

Data Index: 298844 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0432. Min Act: -0.0004

Data Index: 1137229 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0414. Min Act: -0.0004

Data Index: 1356359 (C4 (Web Text))

Max Activating Token Index: 300