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

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

Neuron 2822 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: 0.1624. Min Range: -0.1624

Max Act: 0.1624. Min Act: -0.0001

Data Index: 262386 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1158. Min Act: -0.0001

Data Index: 955510 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1297. Min Act: -0.0001

Data Index: 1616715 (Python Code)

Max Activating Token Index: 565

Text #3

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1188. Min Act: -0.0001

Data Index: 590824 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1264. Min Act: -0.0001

Data Index: 706784 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1256. Min Act: -0.0002

Data Index: 1070534 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1218. Min Act: -0.0002

Data Index: 91045 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1182. Min Act: -0.0002

Data Index: 753909 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1577408 (Python Code)

Max Activating Token Index: 423

Text #9

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1238. Min Act: -0.0002

Data Index: 1392536 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1388009 (Python Code)

Max Activating Token Index: 843

Text #11

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1578205 (Python Code)

Max Activating Token Index: 483

Text #12

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1145. Min Act: -0.0002

Data Index: 843374 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1069146 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1656108 (Python Code)

Max Activating Token Index: 854

Text #15

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1512621 (Python Code)

Max Activating Token Index: 825

Text #16

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1113. Min Act: -0.0002

Data Index: 147431 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1460001 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1459872 (Python Code)

Max Activating Token Index: 839

Text #19

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1061. Min Act: -0.0002

Data Index: 682450 (C4 (Web Text))

Max Activating Token Index: 186