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

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

Neuron 3466 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1484427 (Python Code)

Max Activating Token Index: 919

Text #1

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1498553 (Python Code)

Max Activating Token Index: 695

Text #2

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1426992 (Python Code)

Max Activating Token Index: 349

Text #3

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1518849 (Python Code)

Max Activating Token Index: 278

Text #4

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1653991 (Python Code)

Max Activating Token Index: 852

Text #5

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1455461 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1371401 (Python Code)

Max Activating Token Index: 444

Text #7

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1542058 (Python Code)

Max Activating Token Index: 691

Text #8

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1539480 (Python Code)

Max Activating Token Index: 51

Text #9

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1408659 (Python Code)

Max Activating Token Index: 205

Text #10

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1506365 (Python Code)

Max Activating Token Index: 275

Text #11

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1615659 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1572741 (Python Code)

Max Activating Token Index: 733

Text #13

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1464460 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1540591 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1523924 (Python Code)

Max Activating Token Index: 378

Text #16

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1395449 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1374461 (Python Code)

Max Activating Token Index: 536

Text #18

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1583020 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.3870. Min Act: -0.0000

Data Index: 499277 (C4 (Web Text))

Max Activating Token Index: 831