Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5401 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1092. Min Range: -4.1092

Max Act: 4.1092. Min Act: -0.0000

Data Index: 629195 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 4.1092. Min Range: -4.1092

Max Act: 3.8292. Min Act: -0.0000

Data Index: 715833 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 4.1092. Min Range: -4.1092

Max Act: 3.6617. Min Act: -0.0000

Data Index: 715342 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.1092. Min Range: -4.1092

Max Act: 3.7108. Min Act: -0.0000

Data Index: 508335 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 4.1092. Min Range: -4.1092

Max Act: 3.4596. Min Act: -0.0000

Data Index: 1037206 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 4.1092. Min Range: -4.1092

Max Act: 3.1290. Min Act: -0.0000

Data Index: 774434 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 4.1092. Min Range: -4.1092

Max Act: 3.1050. Min Act: -0.0000

Data Index: 1048109 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 4.1092. Min Range: -4.1092

Max Act: 3.2562. Min Act: -0.0000

Data Index: 1215225 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.9160. Min Act: -0.0000

Data Index: 467453 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.7616. Min Act: -0.0000

Data Index: 565444 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.8745. Min Act: -0.0000

Data Index: 278283 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.7888. Min Act: -0.0000

Data Index: 321501 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.7764. Min Act: -0.0000

Data Index: 1296462 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.6869. Min Act: -0.0000

Data Index: 957854 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.5973. Min Act: -0.0000

Data Index: 1189910 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.7155. Min Act: -0.0000

Data Index: 841549 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.5898. Min Act: -0.0000

Data Index: 814236 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.7208. Min Act: -0.0000

Data Index: 756639 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.4240. Min Act: -0.0000

Data Index: 609443 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 4.1092. Min Range: -4.1092

Max Act: 2.5493. Min Act: -0.0000

Data Index: 570238 (C4 (Web Text))

Max Activating Token Index: 970