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

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

Neuron 1343 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.7045. Min Act: -0.0000

Data Index: 1355806 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.5588. Min Act: -0.0000

Data Index: 1227401 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.3020. Min Act: -0.0000

Data Index: 208461 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 5.7045. Min Range: -5.7045

Max Act: 3.8198. Min Act: -0.0001

Data Index: 451594 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 5.7045. Min Range: -5.7045

Max Act: 3.4392. Min Act: -0.0000

Data Index: 325707 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 5.7045. Min Range: -5.7045

Max Act: 3.1501. Min Act: -0.0001

Data Index: 455196 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.9152. Min Act: -0.0001

Data Index: 323500 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 5.7045. Min Range: -5.7045

Max Act: 3.0018. Min Act: -0.0000

Data Index: 8229 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.8674. Min Act: -0.0000

Data Index: 555414 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.8584. Min Act: -0.0000

Data Index: 589815 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.7753. Min Act: -0.0001

Data Index: 1215408 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.6296. Min Act: -0.0000

Data Index: 129660 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.5923. Min Act: -0.0000

Data Index: 574868 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.5758. Min Act: -0.0000

Data Index: 958759 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.6653. Min Act: -0.0001

Data Index: 708267 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.5167. Min Act: -0.0000

Data Index: 157040 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.7660. Min Act: -0.0001

Data Index: 1129185 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.4887. Min Act: -0.0000

Data Index: 691725 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.5647. Min Act: -0.0000

Data Index: 1118145 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 5.7045. Min Range: -5.7045

Max Act: 2.8328. Min Act: -0.0001

Data Index: 299927 (C4 (Web Text))

Max Activating Token Index: 339