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

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

Neuron 3548 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.7271. Min Act: -0.0000

Data Index: 882583 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.7018. Min Act: -0.0000

Data Index: 641444 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.6205. Min Act: -0.0000

Data Index: 345134 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.6593. Min Act: -0.0000

Data Index: 145059 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1481921 (Python Code)

Max Activating Token Index: 407

Text #5

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.6415. Min Act: -0.0000

Data Index: 596635 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.6115. Min Act: -0.0000

Data Index: 900394 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5837. Min Act: -0.0000

Data Index: 823368 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1346408 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5495. Min Act: -0.0000

Data Index: 615101 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1403845 (Python Code)

Max Activating Token Index: 442

Text #11

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5596. Min Act: -0.0000

Data Index: 617410 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5522. Min Act: -0.0000

Data Index: 836728 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5541. Min Act: -0.0000

Data Index: 168341 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1556642 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1527699 (Python Code)

Max Activating Token Index: 684

Text #16

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5243. Min Act: -0.0000

Data Index: 234236 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.4960. Min Act: -0.0000

Data Index: 28164 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1446541 (Python Code)

Max Activating Token Index: 225

Text #19

Max Range: 0.7271. Min Range: -0.7271

Max Act: 0.5105. Min Act: -0.0000

Data Index: 692326 (C4 (Web Text))

Max Activating Token Index: 441