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

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

Neuron 3743 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: 0.9007. Min Range: -0.9007

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1385095 (Python Code)

Max Activating Token Index: 772

Text #1

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1611125 (Python Code)

Max Activating Token Index: 1003

Text #2

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1592348 (Python Code)

Max Activating Token Index: 648

Text #3

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1511180 (Python Code)

Max Activating Token Index: 912

Text #4

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1551848 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1562022 (Python Code)

Max Activating Token Index: 983

Text #6

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.6437. Min Act: -0.0000

Data Index: 1549199 (Python Code)

Max Activating Token Index: 582

Text #7

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.6545. Min Act: -0.0000

Data Index: 382462 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1603441 (Python Code)

Max Activating Token Index: 1019

Text #9

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1542896 (Python Code)

Max Activating Token Index: 161

Text #10

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1525247 (Python Code)

Max Activating Token Index: 659

Text #11

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1498473 (Python Code)

Max Activating Token Index: 921

Text #12

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.6369. Min Act: -0.0000

Data Index: 875877 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.5648. Min Act: -0.0000

Data Index: 257009 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1451605 (Python Code)

Max Activating Token Index: 1007

Text #15

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1574534 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1595465 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1304149 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.5635. Min Act: -0.0000

Data Index: 688686 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1476486 (Python Code)

Max Activating Token Index: 800