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

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

Neuron 377 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: 0.5070. Min Range: -0.5070

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1574072 (Python Code)

Max Activating Token Index: 1007

Text #1

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1371497 (Python Code)

Max Activating Token Index: 839

Text #2

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1560164 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1428344 (Python Code)

Max Activating Token Index: 692

Text #4

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1637925 (Python Code)

Max Activating Token Index: 574

Text #5

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1558925 (Python Code)

Max Activating Token Index: 520

Text #6

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1581169 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1592220 (Python Code)

Max Activating Token Index: 597

Text #8

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1492370 (Python Code)

Max Activating Token Index: 298

Text #9

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1475358 (Python Code)

Max Activating Token Index: 1014

Text #10

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1649622 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4633. Min Act: -0.0000

Data Index: 1625801 (Python Code)

Max Activating Token Index: 734

Text #12

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1486820 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1568732 (Python Code)

Max Activating Token Index: 375

Text #14

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1500055 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1481486 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1656178 (Python Code)

Max Activating Token Index: 567

Text #17

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1476276 (Python Code)

Max Activating Token Index: 981

Text #18

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1533409 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1591633 (Python Code)

Max Activating Token Index: 656