Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6055 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.8553. Min Act: -0.0000

Data Index: 105948 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.5596. Min Act: -0.0000

Data Index: 1098270 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.2869. Min Act: -0.0000

Data Index: 1165241 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.2655. Min Act: -0.0000

Data Index: 401885 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.1863. Min Act: -0.0000

Data Index: 340043 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.0544. Min Act: -0.0000

Data Index: 585957 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.1238. Min Act: -0.0000

Data Index: 180991 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.1951. Min Act: -0.0000

Data Index: 431297 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.1721. Min Act: -0.0000

Data Index: 25934 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.0402. Min Act: -0.0000

Data Index: 323262 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.0813. Min Act: -0.0000

Data Index: 1358535 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.1253. Min Act: -0.0000

Data Index: 134390 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.8553. Min Range: -1.8553

Max Act: 0.9903. Min Act: -0.0000

Data Index: 211334 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 1.8553. Min Range: -1.8553

Max Act: 0.9080. Min Act: -0.0000

Data Index: 250660 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1007824 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 1.8553. Min Range: -1.8553

Max Act: 0.9368. Min Act: -0.0000

Data Index: 110537 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.0295. Min Act: -0.0000

Data Index: 82797 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.8553. Min Range: -1.8553

Max Act: 0.9966. Min Act: -0.0000

Data Index: 586573 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 1.8553. Min Range: -1.8553

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1054866 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.8553. Min Range: -1.8553

Max Act: 0.9765. Min Act: -0.0000

Data Index: 938425 (C4 (Web Text))

Max Activating Token Index: 479