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

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

Neuron 3488 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0000

Data Index: 269413 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1101701 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0640. Min Act: -0.0000

Data Index: 326960 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0641. Min Act: -0.0000

Data Index: 595018 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0609. Min Act: -0.0000

Data Index: 20958 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0629. Min Act: -0.0000

Data Index: 136699 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0581. Min Act: -0.0000

Data Index: 490161 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1346077 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0561. Min Act: -0.0000

Data Index: 748402 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0577. Min Act: -0.0000

Data Index: 400364 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0524. Min Act: -0.0000

Data Index: 239644 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0525. Min Act: -0.0000

Data Index: 211313 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0527. Min Act: -0.0000

Data Index: 208874 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0540. Min Act: -0.0000

Data Index: 383939 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1323066 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0490. Min Act: -0.0000

Data Index: 763611 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1013088 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0510. Min Act: -0.0000

Data Index: 925234 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0505. Min Act: -0.0000

Data Index: 793584 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0503. Min Act: -0.0000

Data Index: 772754 (C4 (Web Text))

Max Activating Token Index: 703