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

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

Neuron 474 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: 1.6222. Min Range: -1.6222

Max Act: 1.6222. Min Act: -0.0001

Data Index: 1547784 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.5516. Min Act: -0.0001

Data Index: 905898 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.5167. Min Act: -0.0001

Data Index: 360803 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.4820. Min Act: -0.0001

Data Index: 638232 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.5298. Min Act: -0.0001

Data Index: 1211353 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.5600. Min Act: -0.0001

Data Index: 447642 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.5600. Min Act: -0.0001

Data Index: 376624 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.5849. Min Act: -0.0001

Data Index: 1288223 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.4921. Min Act: -0.0001

Data Index: 760061 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.5860. Min Act: -0.0001

Data Index: 417370 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.5166. Min Act: -0.0001

Data Index: 882945 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.5015. Min Act: -0.0001

Data Index: 1042130 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.4274. Min Act: -0.0001

Data Index: 583515 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.4694. Min Act: -0.0001

Data Index: 155691 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.4113. Min Act: -0.0001

Data Index: 37480 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.3718. Min Act: -0.0001

Data Index: 1434357 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.3871. Min Act: -0.0001

Data Index: 631703 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.5158. Min Act: -0.0001

Data Index: 544267 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.3883. Min Act: -0.0001

Data Index: 329429 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 1.6222. Min Range: -1.6222

Max Act: 1.3373. Min Act: -0.0001

Data Index: 1244026 (C4 (Web Text))

Max Activating Token Index: 11