Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 367 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1763. Min Act: -0.0001

Data Index: 932944 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1598. Min Act: -0.0001

Data Index: 988075 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1687. Min Act: -0.0001

Data Index: 45169 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1748. Min Act: -0.0001

Data Index: 807551 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1313501 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1847. Min Act: -0.0001

Data Index: 807601 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1599. Min Act: -0.0001

Data Index: 757379 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1680. Min Act: -0.0001

Data Index: 533432 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1060334 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1699. Min Act: -0.0001

Data Index: 464099 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1313108 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1635. Min Act: -0.0001

Data Index: 252569 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1427. Min Act: -0.0001

Data Index: 413433 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1375668 (Python Code)

Max Activating Token Index: 445

Text #14

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1235957 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1519. Min Act: -0.0001

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1286125 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1389. Min Act: -0.0001

Data Index: 222595 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1352. Min Act: -0.0001

Data Index: 654305 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1506. Min Act: -0.0001

Data Index: 425510 (C4 (Web Text))

Max Activating Token Index: 527