Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3432 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4114. Min Range: -4.4114

Max Act: 4.4114. Min Act: -0.0000

Data Index: 630097 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 4.4114. Min Range: -4.4114

Max Act: 4.0199. Min Act: -0.0000

Data Index: 580473 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.8160. Min Act: -0.0000

Data Index: 960920 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.5670. Min Act: -0.0000

Data Index: 81790 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.5532. Min Act: -0.0000

Data Index: 809283 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.5165. Min Act: -0.0000

Data Index: 699493 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.4970. Min Act: -0.0000

Data Index: 321864 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.3922. Min Act: -0.0000

Data Index: 733255 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.4684. Min Act: -0.0000

Data Index: 97130 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.4529. Min Act: -0.0000

Data Index: 727384 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.2710. Min Act: -0.0000

Data Index: 683540 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.3850. Min Act: -0.0000

Data Index: 832624 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.2016. Min Act: -0.0000

Data Index: 825887 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.1866. Min Act: -0.0000

Data Index: 840006 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.1622. Min Act: -0.0000

Data Index: 1086115 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.0126. Min Act: -0.0000

Data Index: 1016865 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 4.4114. Min Range: -4.4114

Max Act: 2.9734. Min Act: -0.0000

Data Index: 21032 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.1264. Min Act: -0.0000

Data Index: 867334 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.1003. Min Act: -0.0000

Data Index: 458104 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 4.4114. Min Range: -4.4114

Max Act: 3.0878. Min Act: -0.0000

Data Index: 1000963 (C4 (Web Text))

Max Activating Token Index: 273