Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1865 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5994. Min Act: -0.0000

Data Index: 375241 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5732. Min Act: -0.0000

Data Index: 356565 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5708. Min Act: -0.0000

Data Index: 420436 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5535. Min Act: -0.0000

Data Index: 752764 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4588. Min Act: -0.0000

Data Index: 583921 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4645. Min Act: -0.0000

Data Index: 2409 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1201433 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.5098. Min Act: -0.0000

Data Index: 221088 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1567474 (Python Code)

Max Activating Token Index: 594

Text #9

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4581. Min Act: -0.0000

Data Index: 585828 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4487. Min Act: -0.0000

Data Index: 819081 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1347298 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1448668 (Python Code)

Max Activating Token Index: 638

Text #13

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3875. Min Act: -0.0000

Data Index: 788495 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1636135 (Python Code)

Max Activating Token Index: 924

Text #15

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3933. Min Act: -0.0000

Data Index: 322603 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3762. Min Act: -0.0000

Data Index: 555574 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.4011. Min Act: -0.0000

Data Index: 987591 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3659. Min Act: -0.0000

Data Index: 485331 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.5994. Min Range: -0.5994

Max Act: 0.3543. Min Act: -0.0000

Data Index: 823268 (C4 (Web Text))

Max Activating Token Index: 331