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

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

Neuron 1054 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: 1.8253. Min Range: -1.8253

Max Act: 1.8253. Min Act: -0.0001

Data Index: 1479034 (Python Code)

Max Activating Token Index: 419

Text #1

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.7945. Min Act: -0.0001

Data Index: 1636017 (Python Code)

Max Activating Token Index: 939

Text #2

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.7104. Min Act: -0.0001

Data Index: 1419510 (Python Code)

Max Activating Token Index: 322

Text #3

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.3953. Min Act: -0.0001

Data Index: 1580649 (Python Code)

Max Activating Token Index: 146

Text #4

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.2742. Min Act: -0.0001

Data Index: 1378116 (Python Code)

Max Activating Token Index: 631

Text #5

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.4798. Min Act: -0.0001

Data Index: 1427070 (Python Code)

Max Activating Token Index: 671

Text #6

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.3202. Min Act: -0.0000

Data Index: 1380418 (Python Code)

Max Activating Token Index: 141

Text #7

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.1882. Min Act: -0.0000

Data Index: 1467406 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.3454. Min Act: -0.0000

Data Index: 1575382 (Python Code)

Max Activating Token Index: 260

Text #9

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.2010. Min Act: -0.0001

Data Index: 1571818 (Python Code)

Max Activating Token Index: 153

Text #10

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.1129. Min Act: -0.0001

Data Index: 1206871 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.1899. Min Act: -0.0001

Data Index: 1445027 (Python Code)

Max Activating Token Index: 920

Text #12

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.1576. Min Act: -0.0000

Data Index: 1627121 (Python Code)

Max Activating Token Index: 706

Text #13

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.1908. Min Act: -0.0001

Data Index: 1615434 (Python Code)

Max Activating Token Index: 472

Text #14

Max Range: 1.8253. Min Range: -1.8253

Max Act: 0.9977. Min Act: -0.0001

Data Index: 1582202 (Python Code)

Max Activating Token Index: 204

Text #15

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.1652. Min Act: -0.0001

Data Index: 1548208 (Python Code)

Max Activating Token Index: 779

Text #16

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.1272. Min Act: -0.0001

Data Index: 1509119 (Python Code)

Max Activating Token Index: 57

Text #17

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.0159. Min Act: -0.0001

Data Index: 1546272 (Python Code)

Max Activating Token Index: 762

Text #18

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.0750. Min Act: -0.0001

Data Index: 1487795 (Python Code)

Max Activating Token Index: 794

Text #19

Max Range: 1.8253. Min Range: -1.8253

Max Act: 1.0202. Min Act: -0.0001

Data Index: 1019767 (C4 (Web Text))

Max Activating Token Index: 592