Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3147 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1896. Min Act: -0.0001

Data Index: 1373844 (Python Code)

Max Activating Token Index: 263

Text #1

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2671. Min Act: -0.0001

Data Index: 1572052 (Python Code)

Max Activating Token Index: 93

Text #2

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0846. Min Act: -0.0001

Data Index: 1165876 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0520. Min Act: -0.0001

Data Index: 1459039 (Python Code)

Max Activating Token Index: 793

Text #4

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0802. Min Act: -0.0001

Data Index: 53032 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0468. Min Act: -0.0001

Data Index: 1408310 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9982. Min Act: -0.0001

Data Index: 833913 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9696. Min Act: -0.0001

Data Index: 1457176 (Python Code)

Max Activating Token Index: 508

Text #8

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.8674. Min Act: -0.0001

Data Index: 1634985 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0565. Min Act: -0.0000

Data Index: 1379004 (Python Code)

Max Activating Token Index: 607

Text #10

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9578. Min Act: -0.0000

Data Index: 1431352 (Python Code)

Max Activating Token Index: 90

Text #11

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1512734 (Python Code)

Max Activating Token Index: 395

Text #12

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9373. Min Act: -0.0001

Data Index: 1540674 (Python Code)

Max Activating Token Index: 541

Text #13

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9924. Min Act: -0.0001

Data Index: 472666 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0019. Min Act: -0.0001

Data Index: 275728 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1477542 (Python Code)

Max Activating Token Index: 892

Text #16

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.7607. Min Act: -0.0001

Data Index: 932601 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9408. Min Act: -0.0001

Data Index: 1586404 (Python Code)

Max Activating Token Index: 811

Text #18

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.8592. Min Act: -0.0001

Data Index: 903363 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9017. Min Act: -0.0000

Data Index: 1485741 (Python Code)

Max Activating Token Index: 453