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

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

Neuron 4529 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: 2.7075. Min Range: -2.7075

Max Act: 2.7075. Min Act: -0.0000

Data Index: 1112326 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.5407. Min Act: -0.0000

Data Index: 147395 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.5273. Min Act: -0.0000

Data Index: 1009650 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.4503. Min Act: -0.0000

Data Index: 1349555 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.5407. Min Act: -0.0000

Data Index: 1269068 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.3879. Min Act: -0.0000

Data Index: 759744 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.3983. Min Act: -0.0000

Data Index: 1173573 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.3214. Min Act: -0.0000

Data Index: 647011 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.4250. Min Act: -0.0000

Data Index: 647431 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.4180. Min Act: -0.0000

Data Index: 749602 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.4116. Min Act: -0.0000

Data Index: 1333866 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.3561. Min Act: -0.0000

Data Index: 1043172 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.2155. Min Act: -0.0000

Data Index: 1160140 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.4543. Min Act: -0.0000

Data Index: 462274 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.1973. Min Act: -0.0000

Data Index: 1151675 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.4337. Min Act: -0.0000

Data Index: 346786 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.2153. Min Act: -0.0000

Data Index: 481631 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.2243. Min Act: -0.0000

Data Index: 164627 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.2112. Min Act: -0.0000

Data Index: 791826 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 2.7075. Min Range: -2.7075

Max Act: 2.0803. Min Act: -0.0000

Data Index: 257734 (C4 (Web Text))

Max Activating Token Index: 679