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

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

Neuron 63 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.6489. Min Act: 0.0000

Data Index: 1591610 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.4972. Min Act: -0.0000

Data Index: 1391363 (Python Code)

Max Activating Token Index: 460

Text #2

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.2991. Min Act: -0.0000

Data Index: 1477267 (Python Code)

Max Activating Token Index: 489

Text #3

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.0946. Min Act: -0.0000

Data Index: 1298831 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.9259. Min Act: -0.0000

Data Index: 567869 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.9048. Min Act: -0.0000

Data Index: 1515114 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.9047. Min Act: 0.0002

Data Index: 1639704 (Python Code)

Max Activating Token Index: 694

Text #7

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.7704. Min Act: 0.0002

Data Index: 1392934 (Python Code)

Max Activating Token Index: 364

Text #8

Max Range: 3.6489. Min Range: -3.6489

Max Act: 3.0173. Min Act: -0.0000

Data Index: 1554544 (Python Code)

Max Activating Token Index: 693

Text #9

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.9226. Min Act: -0.0000

Data Index: 1267076 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.7636. Min Act: 0.0001

Data Index: 1607342 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.6302. Min Act: -0.0000

Data Index: 1580416 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.7622. Min Act: 0.0002

Data Index: 1442783 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.8703. Min Act: 0.0000

Data Index: 1484185 (Python Code)

Max Activating Token Index: 38

Text #14

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.6612. Min Act: 0.0000

Data Index: 1605580 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.6483. Min Act: -0.0000

Data Index: 1380473 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.7283. Min Act: -0.0000

Data Index: 1481146 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.5784. Min Act: 0.0000

Data Index: 1543990 (Python Code)

Max Activating Token Index: 916

Text #18

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.6967. Min Act: -0.0000

Data Index: 1558694 (Python Code)

Max Activating Token Index: 714

Text #19

Max Range: 3.6489. Min Range: -3.6489

Max Act: 2.4228. Min Act: 0.0000

Data Index: 1459388 (Python Code)

Max Activating Token Index: 137