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

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

Neuron 2871 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: 1.0738. Min Range: -1.0738

Max Act: 1.0738. Min Act: -0.0001

Data Index: 701406 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.9826. Min Act: -0.0001

Data Index: 765969 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.8168. Min Act: -0.0001

Data Index: 1170800 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.9504. Min Act: -0.0001

Data Index: 81490 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.9551. Min Act: -0.0001

Data Index: 365388 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7935. Min Act: -0.0001

Data Index: 1208568 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7950. Min Act: -0.0001

Data Index: 367704 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.6322. Min Act: -0.0001

Data Index: 346151 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7588. Min Act: -0.0001

Data Index: 1141877 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7481. Min Act: -0.0001

Data Index: 161037 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.6117. Min Act: -0.0001

Data Index: 346683 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.6954. Min Act: -0.0001

Data Index: 342835 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7394. Min Act: -0.0001

Data Index: 881626 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7134. Min Act: -0.0001

Data Index: 279183 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.6953. Min Act: -0.0001

Data Index: 385763 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7146. Min Act: -0.0001

Data Index: 777472 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.5996. Min Act: -0.0001

Data Index: 1181653 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.5954. Min Act: -0.0001

Data Index: 341592 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.6887. Min Act: -0.0001

Data Index: 110723 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.0738. Min Range: -1.0738

Max Act: 0.7291. Min Act: -0.0001

Data Index: 396750 (C4 (Web Text))

Max Activating Token Index: 278