Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2613 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4977. Min Act: -0.0001

Data Index: 576024 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4500. Min Act: -0.0001

Data Index: 309412 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4362. Min Act: -0.0001

Data Index: 257587 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4232. Min Act: -0.0001

Data Index: 424882 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4260. Min Act: -0.0001

Data Index: 871556 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4313. Min Act: -0.0001

Data Index: 388848 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4159. Min Act: -0.0001

Data Index: 734670 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4092. Min Act: -0.0001

Data Index: 666464 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3902. Min Act: -0.0001

Data Index: 91163 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3838. Min Act: -0.0001

Data Index: 1277214 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3786. Min Act: -0.0001

Data Index: 242893 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3927. Min Act: -0.0001

Data Index: 661386 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3910. Min Act: -0.0001

Data Index: 181905 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3888. Min Act: -0.0001

Data Index: 573671 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3887. Min Act: -0.0001

Data Index: 181615 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3843. Min Act: -0.0001

Data Index: 957746 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3855. Min Act: -0.0001

Data Index: 11759 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3808. Min Act: -0.0001

Data Index: 1313140 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3642. Min Act: -0.0001

Data Index: 650010 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3802. Min Act: -0.0001

Data Index: 799327 (C4 (Web Text))

Max Activating Token Index: 279