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

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

Neuron 559 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: 1.0104. Min Range: -1.0104

Max Act: 1.0104. Min Act: -0.0001

Data Index: 1515443 (Python Code)

Max Activating Token Index: 304

Text #1

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.8899. Min Act: -0.0001

Data Index: 1372391 (Python Code)

Max Activating Token Index: 158

Text #2

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.8896. Min Act: -0.0001

Data Index: 1536152 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.8853. Min Act: -0.0001

Data Index: 1566211 (Python Code)

Max Activating Token Index: 97

Text #4

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.8680. Min Act: -0.0001

Data Index: 1429310 (Python Code)

Max Activating Token Index: 338

Text #5

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7334. Min Act: -0.0001

Data Index: 1390687 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7493. Min Act: -0.0001

Data Index: 1632559 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7511. Min Act: -0.0001

Data Index: 1449222 (Python Code)

Max Activating Token Index: 422

Text #8

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7401. Min Act: -0.0001

Data Index: 1406403 (Python Code)

Max Activating Token Index: 684

Text #9

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7235. Min Act: -0.0001

Data Index: 1363599 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7960. Min Act: -0.0001

Data Index: 1451881 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6684. Min Act: -0.0001

Data Index: 1401163 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6928. Min Act: -0.0001

Data Index: 1514147 (Python Code)

Max Activating Token Index: 431

Text #13

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7082. Min Act: -0.0001

Data Index: 1370879 (Python Code)

Max Activating Token Index: 801

Text #14

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6785. Min Act: -0.0001

Data Index: 1417716 (Python Code)

Max Activating Token Index: 132

Text #15

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7092. Min Act: -0.0001

Data Index: 1614365 (Python Code)

Max Activating Token Index: 158

Text #16

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.7205. Min Act: -0.0001

Data Index: 1369010 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6408. Min Act: -0.0001

Data Index: 1461895 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6812. Min Act: -0.0001

Data Index: 1486875 (Python Code)

Max Activating Token Index: 456

Text #19

Max Range: 1.0104. Min Range: -1.0104

Max Act: 0.6053. Min Act: -0.0001

Data Index: 1410831 (Python Code)

Max Activating Token Index: 254