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

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

Neuron 2674 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3773. Min Range: -2.3773

Max Act: 2.3773. Min Act: -0.0000

Data Index: 360033 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 2.3773. Min Range: -2.3773

Max Act: 2.1404. Min Act: -0.0000

Data Index: 1086272 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 2.3773. Min Range: -2.3773

Max Act: 2.1263. Min Act: -0.0001

Data Index: 600174 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8948. Min Act: -0.0001

Data Index: 152725 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 2.3773. Min Range: -2.3773

Max Act: 2.0229. Min Act: -0.0001

Data Index: 273826 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.9348. Min Act: -0.0001

Data Index: 513029 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8671. Min Act: -0.0001

Data Index: 1267803 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 2.3773. Min Range: -2.3773

Max Act: 2.0434. Min Act: -0.0001

Data Index: 1002714 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.9080. Min Act: -0.0000

Data Index: 911690 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8902. Min Act: -0.0000

Data Index: 1051256 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8725. Min Act: -0.0001

Data Index: 196581 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.7704. Min Act: -0.0000

Data Index: 8328 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8690. Min Act: -0.0000

Data Index: 1012331 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8374. Min Act: -0.0000

Data Index: 566166 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8540. Min Act: -0.0000

Data Index: 975590 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8233. Min Act: -0.0000

Data Index: 563931 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8293. Min Act: -0.0000

Data Index: 720423 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8051. Min Act: -0.0000

Data Index: 211702 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.8039. Min Act: -0.0000

Data Index: 1213280 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 2.3773. Min Range: -2.3773

Max Act: 1.7842. Min Act: -0.0001

Data Index: 742623 (C4 (Web Text))

Max Activating Token Index: 536