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

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

Neuron 2520 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: 0.8585. Min Range: -0.8585

Max Act: 0.7052. Min Act: -0.0002

Data Index: 1290323 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.8585. Min Act: -0.0002

Data Index: 140564 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7891. Min Act: -0.0001

Data Index: 1291270 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7759. Min Act: -0.0001

Data Index: 300803 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7941. Min Act: -0.0001

Data Index: 1052398 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7002. Min Act: -0.0001

Data Index: 698122 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7201. Min Act: -0.0002

Data Index: 920055 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6576. Min Act: -0.0002

Data Index: 1108188 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7239. Min Act: -0.0001

Data Index: 222035 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7107. Min Act: -0.0001

Data Index: 919232 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7333. Min Act: -0.0001

Data Index: 1142780 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7568. Min Act: -0.0001

Data Index: 248638 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7015. Min Act: -0.0001

Data Index: 803839 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6225. Min Act: -0.0001

Data Index: 217471 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.7621. Min Act: -0.0001

Data Index: 642154 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6508. Min Act: -0.0001

Data Index: 583196 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6938. Min Act: -0.0001

Data Index: 94459 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6684. Min Act: -0.0001

Data Index: 409420 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6640. Min Act: -0.0002

Data Index: 959562 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.8585. Min Range: -0.8585

Max Act: 0.6462. Min Act: -0.0001

Data Index: 969947 (C4 (Web Text))

Max Activating Token Index: 632