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

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

Neuron 1728 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: 0.5994. Min Range: -0.5994

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1434925 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1510596 (Python Code)

Max Activating Token Index: 82

Text #2

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1540102 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1550815 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1610558 (Python Code)

Max Activating Token Index: 188

Text #5

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1575793 (Python Code)

Max Activating Token Index: 362

Text #6

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1369050 (Python Code)

Max Activating Token Index: 132

Text #7

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1408911 (Python Code)

Max Activating Token Index: 500

Text #8

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1470029 (Python Code)

Max Activating Token Index: 331

Text #9

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1412464 (Python Code)

Max Activating Token Index: 1015

Text #10

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1550702 (Python Code)

Max Activating Token Index: 572

Text #11

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4744. Min Act: -0.0000

Data Index: 559102 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1594213 (Python Code)

Max Activating Token Index: 469

Text #13

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1485212 (Python Code)

Max Activating Token Index: 507

Text #14

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1515297 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1406240 (Python Code)

Max Activating Token Index: 976

Text #16

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1439008 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1510510 (Python Code)

Max Activating Token Index: 394

Text #18

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1464915 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1614907 (Python Code)

Max Activating Token Index: 352