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

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

Neuron 1795 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0128. Min Act: -0.0001

Data Index: 1561223 (Python Code)

Max Activating Token Index: 530

Text #1

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0117. Min Act: -0.0001

Data Index: 501155 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0112. Min Act: -0.0001

Data Index: 809621 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0116. Min Act: -0.0001

Data Index: 322489 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0115. Min Act: -0.0001

Data Index: 1134844 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0113. Min Act: -0.0001

Data Index: 993059 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0102. Min Act: -0.0001

Data Index: 310591 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0110. Min Act: -0.0001

Data Index: 1266601 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0110. Min Act: -0.0001

Data Index: 1222063 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0105. Min Act: -0.0001

Data Index: 1213768 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0106. Min Act: -0.0001

Data Index: 610768 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0102. Min Act: -0.0001

Data Index: 1591203 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0105. Min Act: -0.0001

Data Index: 889469 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0094. Min Act: -0.0001

Data Index: 644943 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0107. Min Act: -0.0001

Data Index: 992575 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0112. Min Act: -0.0001

Data Index: 648368 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0105. Min Act: -0.0001

Data Index: 1194640 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0104. Min Act: -0.0001

Data Index: 218685 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0105. Min Act: -0.0001

Data Index: 1149546 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0098. Min Act: -0.0001

Data Index: 690187 (C4 (Web Text))

Max Activating Token Index: 510