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

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

Neuron 4733 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: 0.5383. Min Range: -0.5383

Max Act: 0.5273. Min Act: -0.0001

Data Index: 1516132 (Python Code)

Max Activating Token Index: 321

Text #1

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5268. Min Act: -0.0001

Data Index: 1524424 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1601362 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5292. Min Act: -0.0001

Data Index: 1572475 (Python Code)

Max Activating Token Index: 270

Text #4

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1414769 (Python Code)

Max Activating Token Index: 203

Text #5

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1508116 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1537592 (Python Code)

Max Activating Token Index: 786

Text #7

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1467271 (Python Code)

Max Activating Token Index: 939

Text #8

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5383. Min Act: -0.0001

Data Index: 1455747 (Python Code)

Max Activating Token Index: 178

Text #9

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1460584 (Python Code)

Max Activating Token Index: 593

Text #10

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5022. Min Act: -0.0001

Data Index: 1575102 (Python Code)

Max Activating Token Index: 508

Text #11

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4857. Min Act: -0.0001

Data Index: 1393770 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1462957 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1384316 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4757. Min Act: -0.0001

Data Index: 1595180 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1557746 (Python Code)

Max Activating Token Index: 133

Text #16

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1530278 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4830. Min Act: -0.0001

Data Index: 1520170 (Python Code)

Max Activating Token Index: 980

Text #18

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1428352 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1524182 (Python Code)

Max Activating Token Index: 396