Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1832 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0736. Min Act: -0.0000

Data Index: 144726 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1353892 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1526818 (Python Code)

Max Activating Token Index: 878

Text #3

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1580635 (Python Code)

Max Activating Token Index: 726

Text #4

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1589140 (Python Code)

Max Activating Token Index: 793

Text #5

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0595. Min Act: -0.0001

Data Index: 91566 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0631. Min Act: -0.0001

Data Index: 850359 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0595. Min Act: -0.0000

Data Index: 617289 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1510627 (Python Code)

Max Activating Token Index: 670

Text #9

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0525. Min Act: -0.0001

Data Index: 320045 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0662. Min Act: -0.0000

Data Index: 864793 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0569. Min Act: -0.0001

Data Index: 332999 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1087790 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0553. Min Act: -0.0001

Data Index: 1460869 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0559. Min Act: -0.0000

Data Index: 99925 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1446956 (Python Code)

Max Activating Token Index: 105

Text #16

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1448874 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0565. Min Act: -0.0001

Data Index: 169307 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1393613 (Python Code)

Max Activating Token Index: 758

Text #19

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1651317 (Python Code)

Max Activating Token Index: 397