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

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

Neuron 455 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1652390 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 1.0614. Min Range: -1.0614

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1410899 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1591333 (Python Code)

Max Activating Token Index: 1022

Text #3

Max Range: 1.0614. Min Range: -1.0614

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1656939 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1383819 (Python Code)

Max Activating Token Index: 165

Text #5

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1571369 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1637375 (Python Code)

Max Activating Token Index: 328

Text #7

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1643341 (Python Code)

Max Activating Token Index: 98

Text #8

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1483037 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1642780 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1612190 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1511916 (Python Code)

Max Activating Token Index: 962

Text #12

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1639944 (Python Code)

Max Activating Token Index: 220

Text #13

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1390094 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1481535 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1451488 (Python Code)

Max Activating Token Index: 672

Text #16

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1539703 (Python Code)

Max Activating Token Index: 556

Text #17

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1558766 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1480668 (Python Code)

Max Activating Token Index: 992

Text #19

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1631878 (Python Code)

Max Activating Token Index: 225