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

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

Neuron 3510 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: 0.7448. Min Range: -0.7448

Max Act: 0.7448. Min Act: -0.0000

Data Index: 1500135 (Python Code)

Max Activating Token Index: 998

Text #1

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.7167. Min Act: -0.0000

Data Index: 539925 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1646968 (Python Code)

Max Activating Token Index: 305

Text #3

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1376234 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1378620 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1486699 (Python Code)

Max Activating Token Index: 151

Text #6

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1558379 (Python Code)

Max Activating Token Index: 189

Text #7

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.5813. Min Act: -0.0000

Data Index: 35249 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1636623 (Python Code)

Max Activating Token Index: 458

Text #9

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1443578 (Python Code)

Max Activating Token Index: 562

Text #10

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1372856 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1549969 (Python Code)

Max Activating Token Index: 495

Text #12

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.6311. Min Act: -0.0000

Data Index: 411811 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.5810. Min Act: -0.0000

Data Index: 504702 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1407355 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1614160 (Python Code)

Max Activating Token Index: 947

Text #16

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.5963. Min Act: -0.0000

Data Index: 956252 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1656299 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.5940. Min Act: -0.0000

Data Index: 56472 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.7448. Min Range: -0.7448

Max Act: 0.5829. Min Act: -0.0000

Data Index: 514410 (C4 (Web Text))

Max Activating Token Index: 761