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

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

Neuron 3421 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.5117. Min Act: -0.0001

Data Index: 239107 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4743. Min Act: -0.0001

Data Index: 130287 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4565. Min Act: -0.0001

Data Index: 713585 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4514. Min Act: -0.0001

Data Index: 972392 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4574. Min Act: -0.0001

Data Index: 1289108 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4450. Min Act: -0.0001

Data Index: 898005 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4298. Min Act: -0.0001

Data Index: 309604 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4250. Min Act: -0.0001

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.3949. Min Act: -0.0001

Data Index: 478498 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.3694. Min Act: -0.0001

Data Index: 727995 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.3024. Min Act: -0.0001

Data Index: 258364 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.3115. Min Act: -0.0001

Data Index: 919621 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.2683. Min Act: -0.0001

Data Index: 291385 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.2884. Min Act: -0.0001

Data Index: 325272 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.2465. Min Act: -0.0001

Data Index: 427571 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.2399. Min Act: -0.0001

Data Index: 227006 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.2582. Min Act: -0.0001

Data Index: 170020 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.2799. Min Act: -0.0001

Data Index: 637733 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.2511. Min Act: -0.0001

Data Index: 1048367 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.2771. Min Act: -0.0001

Data Index: 304978 (C4 (Web Text))

Max Activating Token Index: 246