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

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

Neuron 827 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1597512 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1441359 (Python Code)

Max Activating Token Index: 156

Text #2

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1478791 (Python Code)

Max Activating Token Index: 538

Text #3

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1515551 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.2331. Min Act: -0.0000

Data Index: 1656856 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.1580. Min Act: -0.0000

Data Index: 1421214 (Python Code)

Max Activating Token Index: 922

Text #6

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1486229 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.1200. Min Act: -0.0000

Data Index: 1502178 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.0622. Min Act: -0.0000

Data Index: 1576285 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.1438. Min Act: -0.0000

Data Index: 1566067 (Python Code)

Max Activating Token Index: 688

Text #10

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1647940 (Python Code)

Max Activating Token Index: 408

Text #11

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1413128 (Python Code)

Max Activating Token Index: 93

Text #12

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1411767 (Python Code)

Max Activating Token Index: 398

Text #13

Max Range: 1.7329. Min Range: -1.7329

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1499175 (Python Code)

Max Activating Token Index: 154

Text #14

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1541714 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1569853 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1439369 (Python Code)

Max Activating Token Index: 214

Text #17

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.0462. Min Act: -0.0000

Data Index: 1518559 (Python Code)

Max Activating Token Index: 108

Text #18

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1432583 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 1.7329. Min Range: -1.7329

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1465745 (Python Code)

Max Activating Token Index: 49