Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4381 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.4058. Min Act: -0.0001

Data Index: 359545 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.3852. Min Act: -0.0001

Data Index: 987911 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.3406. Min Act: -0.0001

Data Index: 254999 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.3207. Min Act: -0.0001

Data Index: 933154 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.3173. Min Act: -0.0001

Data Index: 744658 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.3611. Min Act: -0.0001

Data Index: 696521 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.3698. Min Act: -0.0001

Data Index: 586702 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.2630. Min Act: -0.0001

Data Index: 944226 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.4007. Min Act: -0.0001

Data Index: 665721 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.2368. Min Act: -0.0001

Data Index: 1269270 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.1881. Min Act: -0.0001

Data Index: 609392 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.1446. Min Act: -0.0001

Data Index: 342790 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.1673. Min Act: -0.0001

Data Index: 286109 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.1554. Min Act: -0.0001

Data Index: 265882 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.2526. Min Act: -0.0001

Data Index: 1230470 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.1064. Min Act: -0.0001

Data Index: 452838 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.1542. Min Act: -0.0001

Data Index: 1323413 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.1712. Min Act: -0.0001

Data Index: 39699 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.1123. Min Act: -0.0001

Data Index: 1348882 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 1.4058. Min Range: -1.4058

Max Act: 1.1406. Min Act: -0.0001

Data Index: 610888 (C4 (Web Text))

Max Activating Token Index: 505