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

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

Neuron 2510 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: 3.6250. Min Range: -3.6250

Max Act: 3.6250. Min Act: -0.0001

Data Index: 452041 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.3503. Min Act: -0.0000

Data Index: 498877 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.2233. Min Act: -0.0000

Data Index: 941067 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.1052. Min Act: -0.0001

Data Index: 35141 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.0699. Min Act: -0.0001

Data Index: 1248316 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.0925. Min Act: -0.0000

Data Index: 1333962 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.2214. Min Act: -0.0000

Data Index: 1286482 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.1040. Min Act: -0.0001

Data Index: 228803 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.6250. Min Range: -3.6250

Max Act: 2.9697. Min Act: -0.0001

Data Index: 1039805 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.1073. Min Act: -0.0000

Data Index: 709666 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.0390. Min Act: -0.0001

Data Index: 1344386 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.6250. Min Range: -3.6250

Max Act: 2.9909. Min Act: -0.0000

Data Index: 254338 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 3.6250. Min Range: -3.6250

Max Act: 2.6234. Min Act: -0.0001

Data Index: 367147 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 3.6250. Min Range: -3.6250

Max Act: 2.7532. Min Act: -0.0001

Data Index: 595028 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.0135. Min Act: -0.0001

Data Index: 187825 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 3.6250. Min Range: -3.6250

Max Act: 2.9502. Min Act: -0.0000

Data Index: 733183 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 3.6250. Min Range: -3.6250

Max Act: 2.9575. Min Act: -0.0000

Data Index: 817829 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 3.6250. Min Range: -3.6250

Max Act: 2.9553. Min Act: -0.0001

Data Index: 746949 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 3.6250. Min Range: -3.6250

Max Act: 2.6734. Min Act: -0.0001

Data Index: 1301482 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 3.6250. Min Range: -3.6250

Max Act: 3.0792. Min Act: -0.0001

Data Index: 1345786 (C4 (Web Text))

Max Activating Token Index: 518