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

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

Neuron 2929 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.4013. Min Act: -0.0001

Data Index: 1411302 (Python Code)

Max Activating Token Index: 81

Text #1

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3743. Min Act: -0.0001

Data Index: 1412032 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3662. Min Act: -0.0001

Data Index: 1477210 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3644. Min Act: -0.0001

Data Index: 1368812 (Python Code)

Max Activating Token Index: 206

Text #4

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1596226 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3248. Min Act: -0.0001

Data Index: 1420124 (Python Code)

Max Activating Token Index: 146

Text #6

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3342. Min Act: -0.0001

Data Index: 1649046 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1468884 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3034. Min Act: -0.0001

Data Index: 1483339 (Python Code)

Max Activating Token Index: 191

Text #9

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1465389 (Python Code)

Max Activating Token Index: 897

Text #10

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2844. Min Act: -0.0001

Data Index: 1638390 (Python Code)

Max Activating Token Index: 290

Text #11

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3012. Min Act: -0.0001

Data Index: 1396952 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3156. Min Act: -0.0001

Data Index: 1649321 (Python Code)

Max Activating Token Index: 326

Text #13

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2939. Min Act: -0.0001

Data Index: 1492924 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1510562 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1616270 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2919. Min Act: -0.0001

Data Index: 1556700 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1524968 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2875. Min Act: -0.0001

Data Index: 1641718 (Python Code)

Max Activating Token Index: 139

Text #19

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2721. Min Act: -0.0001

Data Index: 1466112 (Python Code)

Max Activating Token Index: 96