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

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

Neuron 5800 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8265. Min Act: -0.0001

Data Index: 661193 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 3.0717. Min Range: -3.0717

Max Act: 3.0717. Min Act: -0.0001

Data Index: 998600 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.4902. Min Act: -0.0001

Data Index: 53873 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.2186. Min Act: -0.0001

Data Index: 500492 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.7388. Min Act: -0.0001

Data Index: 187735 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.3730. Min Act: -0.0001

Data Index: 161309 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.1240. Min Act: -0.0001

Data Index: 271172 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.4095. Min Act: -0.0001

Data Index: 603967 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.5723. Min Act: -0.0000

Data Index: 34458 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.1297. Min Act: -0.0000

Data Index: 278856 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.2410. Min Act: -0.0001

Data Index: 437004 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.0381. Min Act: -0.0000

Data Index: 551400 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.2185. Min Act: -0.0001

Data Index: 1166908 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.2045. Min Act: -0.0001

Data Index: 1265760 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.1606. Min Act: -0.0001

Data Index: 1244658 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.0280. Min Act: -0.0001

Data Index: 1349926 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.0268. Min Act: -0.0001

Data Index: 163422 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 3.0717. Min Range: -3.0717

Max Act: 1.8956. Min Act: -0.0000

Data Index: 612443 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.2989. Min Act: -0.0001

Data Index: 360465 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.2116. Min Act: -0.0001

Data Index: 521030 (C4 (Web Text))

Max Activating Token Index: 1021