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

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

Neuron 1236 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.2082. Min Act: -0.0001

Data Index: 262101 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0714. Min Act: -0.0001

Data Index: 1620606 (Python Code)

Max Activating Token Index: 203

Text #2

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1475142 (Python Code)

Max Activating Token Index: 495

Text #3

Max Range: 1.2082. Min Range: -1.2082

Max Act: 1.0135. Min Act: -0.0001

Data Index: 1464884 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1417683 (Python Code)

Max Activating Token Index: 961

Text #5

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9824. Min Act: -0.0001

Data Index: 1410176 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9742. Min Act: -0.0001

Data Index: 234927 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9563. Min Act: -0.0001

Data Index: 1450209 (Python Code)

Max Activating Token Index: 710

Text #8

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9832. Min Act: -0.0001

Data Index: 1163063 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9381. Min Act: -0.0001

Data Index: 1401977 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9409. Min Act: -0.0001

Data Index: 12379 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1490571 (Python Code)

Max Activating Token Index: 752

Text #12

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.8998. Min Act: -0.0001

Data Index: 1647428 (Python Code)

Max Activating Token Index: 159

Text #13

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9142. Min Act: -0.0001

Data Index: 1375885 (Python Code)

Max Activating Token Index: 894

Text #14

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9300. Min Act: -0.0001

Data Index: 1372523 (Python Code)

Max Activating Token Index: 860

Text #15

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.9273. Min Act: -0.0001

Data Index: 770754 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.8770. Min Act: -0.0001

Data Index: 1514746 (Python Code)

Max Activating Token Index: 968

Text #17

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.8432. Min Act: -0.0001

Data Index: 1639008 (Python Code)

Max Activating Token Index: 796

Text #18

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.8912. Min Act: -0.0001

Data Index: 798640 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.2082. Min Range: -1.2082

Max Act: 0.8878. Min Act: -0.0001

Data Index: 27506 (C4 (Web Text))

Max Activating Token Index: 443