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

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

Neuron 486 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0961. Min Range: -1.0961

Max Act: 1.0961. Min Act: -0.0000

Data Index: 985003 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.8476. Min Act: -0.0000

Data Index: 635242 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.8200. Min Act: -0.0000

Data Index: 518218 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.7900. Min Act: -0.0000

Data Index: 805547 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.7194. Min Act: -0.0000

Data Index: 353796 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.6745. Min Act: -0.0000

Data Index: 456249 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1186063 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1062466 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1163960 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1228346 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.6560. Min Act: -0.0000

Data Index: 743827 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.5965. Min Act: -0.0000

Data Index: 579331 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1308297 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1322644 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.5851. Min Act: -0.0000

Data Index: 520406 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.6227. Min Act: -0.0000

Data Index: 909473 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1086349 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.5780. Min Act: -0.0000

Data Index: 749240 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.5916. Min Act: -0.0000

Data Index: 574687 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 1.0961. Min Range: -1.0961

Max Act: 0.5833. Min Act: -0.0000

Data Index: 709369 (C4 (Web Text))

Max Activating Token Index: 427