Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1786 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.4679. Min Act: -0.0001

Data Index: 719663 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.1792. Min Act: -0.0002

Data Index: 1036988 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.4130. Min Act: -0.0002

Data Index: 237444 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.2246. Min Act: -0.0002

Data Index: 199509 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.1641. Min Act: -0.0002

Data Index: 401791 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.1050. Min Act: -0.0002

Data Index: 233591 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.0997. Min Act: -0.0002

Data Index: 22012 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 1.4679. Min Range: -1.4679

Max Act: 0.9409. Min Act: -0.0002

Data Index: 1214979 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.1126. Min Act: -0.0002

Data Index: 584878 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.1390. Min Act: -0.0002

Data Index: 197306 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.1149. Min Act: -0.0002

Data Index: 604687 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.0950. Min Act: -0.0002

Data Index: 758001 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 1.4679. Min Range: -1.4679

Max Act: 0.9936. Min Act: -0.0001

Data Index: 1159680 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.1220. Min Act: -0.0002

Data Index: 201662 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.0531. Min Act: -0.0001

Data Index: 633657 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 1.4679. Min Range: -1.4679

Max Act: 0.9687. Min Act: -0.0002

Data Index: 503898 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.0764. Min Act: -0.0002

Data Index: 117627 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.0060. Min Act: -0.0001

Data Index: 1329363 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.0635. Min Act: -0.0001

Data Index: 1017481 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 1.4679. Min Range: -1.4679

Max Act: 1.1000. Min Act: -0.0002

Data Index: 992498 (C4 (Web Text))

Max Activating Token Index: 962