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

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

Neuron 3074 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1019. Min Act: -0.0002

Data Index: 573617 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1120. Min Act: -0.0002

Data Index: 661980 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1330688 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1045. Min Act: -0.0002

Data Index: 437314 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1080. Min Act: -0.0001

Data Index: 371631 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0944. Min Act: -0.0001

Data Index: 784892 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1005. Min Act: -0.0002

Data Index: 256314 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1195953 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1211099 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0948. Min Act: -0.0001

Data Index: 316191 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1336812 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1197435 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0919. Min Act: -0.0001

Data Index: 384040 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0851. Min Act: -0.0002

Data Index: 276525 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0888. Min Act: -0.0001

Data Index: 162266 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0899. Min Act: -0.0001

Data Index: 995974 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0830. Min Act: -0.0001

Data Index: 984341 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1247019 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1065140 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0756. Min Act: -0.0002

Data Index: 992451 (C4 (Web Text))

Max Activating Token Index: 244