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

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

Neuron 194 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1428033 (Python Code)

Max Activating Token Index: 574

Text #1

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1381732 (Python Code)

Max Activating Token Index: 553

Text #2

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1468557 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1362220 (Python Code)

Max Activating Token Index: 78

Text #4

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1096500 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1426451 (Python Code)

Max Activating Token Index: 968

Text #6

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1423081 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1634937 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1636409 (Python Code)

Max Activating Token Index: 779

Text #9

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1374018 (Python Code)

Max Activating Token Index: 348

Text #10

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1484726 (Python Code)

Max Activating Token Index: 854

Text #11

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1495836 (Python Code)

Max Activating Token Index: 583

Text #12

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1454744 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7657. Min Act: -0.0000

Data Index: 1459693 (Python Code)

Max Activating Token Index: 599

Text #14

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1561398 (Python Code)

Max Activating Token Index: 47

Text #15

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1487088 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1561785 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1291005 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1534141 (Python Code)

Max Activating Token Index: 527

Text #19

Max Range: 0.9617. Min Range: -0.9617

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1430261 (Python Code)

Max Activating Token Index: 941