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

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

Neuron 5628 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1096463 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1515085 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.4322. Min Act: 0.0000

Data Index: 1591233 (Python Code)

Max Activating Token Index: 946

Text #3

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1650135 (Python Code)

Max Activating Token Index: 607

Text #4

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1435334 (Python Code)

Max Activating Token Index: 444

Text #5

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1639127 (Python Code)

Max Activating Token Index: 191

Text #6

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1506965 (Python Code)

Max Activating Token Index: 497

Text #7

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3946. Min Act: 0.0000

Data Index: 1549797 (Python Code)

Max Activating Token Index: 56

Text #8

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1030875 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1543154 (Python Code)

Max Activating Token Index: 725

Text #10

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.4263. Min Act: 0.0001

Data Index: 1636629 (Python Code)

Max Activating Token Index: 884

Text #11

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1502537 (Python Code)

Max Activating Token Index: 776

Text #12

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1551486 (Python Code)

Max Activating Token Index: 514

Text #13

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1444576 (Python Code)

Max Activating Token Index: 221

Text #14

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1643301 (Python Code)

Max Activating Token Index: 613

Text #15

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3598. Min Act: 0.0000

Data Index: 1492307 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1631343 (Python Code)

Max Activating Token Index: 431

Text #17

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3784. Min Act: -0.0000

Data Index: 187666 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3624. Min Act: 0.0000

Data Index: 1421372 (Python Code)

Max Activating Token Index: 196

Text #19

Max Range: 0.6169. Min Range: -0.6169

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1548324 (Python Code)

Max Activating Token Index: 756