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

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

Neuron 1525 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.4275. Min Act: 0.0000

Data Index: 1547131 (Python Code)

Max Activating Token Index: 543

Text #1

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1529635 (Python Code)

Max Activating Token Index: 324

Text #2

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3983. Min Act: 0.0000

Data Index: 1515415 (Python Code)

Max Activating Token Index: 332

Text #3

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1491226 (Python Code)

Max Activating Token Index: 122

Text #4

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3801. Min Act: 0.0000

Data Index: 1366552 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1377846 (Python Code)

Max Activating Token Index: 861

Text #6

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1639114 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3887. Min Act: 0.0001

Data Index: 1582076 (Python Code)

Max Activating Token Index: 354

Text #8

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1388385 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3719. Min Act: 0.0000

Data Index: 1576499 (Python Code)

Max Activating Token Index: 721

Text #10

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1520945 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1567158 (Python Code)

Max Activating Token Index: 472

Text #12

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1407747 (Python Code)

Max Activating Token Index: 295

Text #13

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1377762 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1370485 (Python Code)

Max Activating Token Index: 646

Text #15

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1616406 (Python Code)

Max Activating Token Index: 302

Text #16

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1552051 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3671. Min Act: 0.0000

Data Index: 1528270 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1384591 (Python Code)

Max Activating Token Index: 524

Text #19

Max Range: 0.4275. Min Range: -0.4275

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1500580 (Python Code)

Max Activating Token Index: 673