Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 987 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5816. Min Range: -2.5816

Max Act: 2.5816. Min Act: -0.0000

Data Index: 1443492 (Python Code)

Max Activating Token Index: 521

Text #1

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.8330. Min Act: -0.0000

Data Index: 1558573 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.8547. Min Act: -0.0000

Data Index: 1595189 (Python Code)

Max Activating Token Index: 228

Text #3

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.6898. Min Act: -0.0000

Data Index: 1511316 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.8452. Min Act: -0.0000

Data Index: 1611723 (Python Code)

Max Activating Token Index: 682

Text #5

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.6168. Min Act: -0.0000

Data Index: 1511897 (Python Code)

Max Activating Token Index: 246

Text #6

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.4714. Min Act: -0.0000

Data Index: 1428925 (Python Code)

Max Activating Token Index: 689

Text #7

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.5894. Min Act: -0.0000

Data Index: 1489122 (Python Code)

Max Activating Token Index: 507

Text #8

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.6547. Min Act: -0.0000

Data Index: 1362705 (Python Code)

Max Activating Token Index: 715

Text #9

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.3919. Min Act: -0.0000

Data Index: 1410206 (Python Code)

Max Activating Token Index: 467

Text #10

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.5745. Min Act: -0.0000

Data Index: 1497316 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.4286. Min Act: -0.0000

Data Index: 1430631 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.4672. Min Act: -0.0000

Data Index: 1567819 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.5756. Min Act: -0.0000

Data Index: 1636548 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.6179. Min Act: -0.0000

Data Index: 1380565 (Python Code)

Max Activating Token Index: 160

Text #15

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1515300 (Python Code)

Max Activating Token Index: 252

Text #16

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.3741. Min Act: -0.0000

Data Index: 1641773 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.3754. Min Act: -0.0000

Data Index: 1493220 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1595223 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 2.5816. Min Range: -2.5816

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1541054 (Python Code)

Max Activating Token Index: 836