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

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

Neuron 3241 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.7093. Min Act: -0.0000

Data Index: 458258 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.5819. Min Act: -0.0000

Data Index: 308089 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.5476. Min Act: -0.0000

Data Index: 992776 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1212976 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.5799. Min Act: -0.0000

Data Index: 69340 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1224859 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4955. Min Act: -0.0000

Data Index: 600953 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1214041 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4827. Min Act: -0.0000

Data Index: 968475 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1294420 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4976. Min Act: -0.0000

Data Index: 771336 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4556. Min Act: -0.0000

Data Index: 520611 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4214. Min Act: -0.0000

Data Index: 711736 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1235314 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4734. Min Act: -0.0000

Data Index: 490074 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4372. Min Act: -0.0000

Data Index: 51714 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4251. Min Act: -0.0000

Data Index: 279668 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4678. Min Act: -0.0000

Data Index: 31859 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4241. Min Act: -0.0000

Data Index: 895026 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.7093. Min Range: -0.7093

Max Act: 0.4099. Min Act: -0.0000

Data Index: 271387 (C4 (Web Text))

Max Activating Token Index: 627