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

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

Neuron 1994 in Layer 5

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: 0.0546. Min Act: -0.0001

Data Index: 550901 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0548. Min Act: -0.0001

Data Index: 855549 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0515. Min Act: -0.0001

Data Index: 477020 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0001

Data Index: 278442 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0591. Min Act: -0.0001

Data Index: 127620 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1409876 (Python Code)

Max Activating Token Index: 414

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0525. Min Act: -0.0001

Data Index: 851977 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0554. Min Act: -0.0001

Data Index: 214675 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1239261 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0533. Min Act: -0.0001

Data Index: 943204 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1419732 (Python Code)

Max Activating Token Index: 829

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1642178 (Python Code)

Max Activating Token Index: 697

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1368983 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0526. Min Act: -0.0001

Data Index: 679769 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1212456 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0425. Min Act: -0.0001

Data Index: 190410 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0548. Min Act: -0.0001

Data Index: 480579 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1344550 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0493. Min Act: -0.0001

Data Index: 1568719 (Python Code)

Max Activating Token Index: 375

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0529. Min Act: -0.0001

Data Index: 27158 (C4 (Web Text))

Max Activating Token Index: 298