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

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

Neuron 214 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: 0.7075. Min Range: -0.7075

Max Act: 0.7075. Min Act: -0.0000

Data Index: 561932 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6135. Min Act: -0.0000

Data Index: 50355 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6715. Min Act: -0.0000

Data Index: 431443 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1496164 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1108261 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5633. Min Act: -0.0000

Data Index: 437468 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5404. Min Act: -0.0000

Data Index: 1365691 (Python Code)

Max Activating Token Index: 464

Text #7

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5313. Min Act: -0.0000

Data Index: 685804 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1096615 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1603394 (Python Code)

Max Activating Token Index: 927

Text #10

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5681. Min Act: 0.0000

Data Index: 1214734 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5317. Min Act: -0.0000

Data Index: 598539 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1536987 (Python Code)

Max Activating Token Index: 780

Text #13

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5174. Min Act: 0.0000

Data Index: 1163588 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5374. Min Act: -0.0000

Data Index: 739899 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1211407 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1190512 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5285. Min Act: -0.0000

Data Index: 661327 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4865. Min Act: 0.0000

Data Index: 1226658 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4868. Min Act: -0.0000

Data Index: 23634 (C4 (Web Text))

Max Activating Token Index: 406