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

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

Neuron 579 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: 0.7904. Min Range: -0.7904

Max Act: 0.7904. Min Act: -0.0000

Data Index: 870559 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7637. Min Act: -0.0000

Data Index: 238708 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1014034 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6979. Min Act: -0.0000

Data Index: 810985 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1354072 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6341. Min Act: -0.0000

Data Index: 612749 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6687. Min Act: -0.0000

Data Index: 967437 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6503. Min Act: -0.0000

Data Index: 250028 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6079. Min Act: -0.0000

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6269. Min Act: -0.0000

Data Index: 133647 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5539. Min Act: -0.0000

Data Index: 302617 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5415. Min Act: -0.0000

Data Index: 310457 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5561. Min Act: -0.0000

Data Index: 140960 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4981. Min Act: -0.0000

Data Index: 619725 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5450. Min Act: -0.0000

Data Index: 117185 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5381. Min Act: -0.0000

Data Index: 739455 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5357. Min Act: -0.0000

Data Index: 719510 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4514. Min Act: -0.0000

Data Index: 284851 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5116. Min Act: -0.0000

Data Index: 551352 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4860. Min Act: -0.0000

Data Index: 851070 (C4 (Web Text))

Max Activating Token Index: 34