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

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

Neuron 3795 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.9642. Min Act: -0.0000

Data Index: 683342 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 2.0103. Min Range: -2.0103

Max Act: 2.0103. Min Act: -0.0001

Data Index: 1222935 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.5793. Min Act: -0.0000

Data Index: 867258 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.6370. Min Act: -0.0001

Data Index: 316661 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.4957. Min Act: -0.0000

Data Index: 106843 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.4041. Min Act: -0.0000

Data Index: 243729 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.3101. Min Act: -0.0000

Data Index: 486751 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.3178. Min Act: -0.0001

Data Index: 90547 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.2201. Min Act: -0.0000

Data Index: 200320 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.2405. Min Act: -0.0000

Data Index: 343268 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.3421. Min Act: -0.0001

Data Index: 1249439 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.3245. Min Act: -0.0001

Data Index: 1351589 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1275297 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.2424. Min Act: -0.0000

Data Index: 821313 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.2502. Min Act: -0.0001

Data Index: 1002490 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.0876. Min Act: -0.0000

Data Index: 296854 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.1470. Min Act: -0.0001

Data Index: 1166997 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.1595. Min Act: -0.0000

Data Index: 1194508 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.1209. Min Act: -0.0001

Data Index: 1199752 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 2.0103. Min Range: -2.0103

Max Act: 1.0907. Min Act: -0.0000

Data Index: 113234 (C4 (Web Text))

Max Activating Token Index: 848