Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3140 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.8989. Min Act: -0.0001

Data Index: 33730 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.8886. Min Act: -0.0001

Data Index: 16590 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.7187. Min Act: -0.0001

Data Index: 1091478 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.7648. Min Act: -0.0001

Data Index: 330539 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.7551. Min Act: -0.0001

Data Index: 875227 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.6875. Min Act: -0.0001

Data Index: 896660 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5870. Min Act: -0.0001

Data Index: 798551 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.6960. Min Act: -0.0001

Data Index: 1000363 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.6490. Min Act: -0.0001

Data Index: 1355165 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5201. Min Act: -0.0001

Data Index: 704393 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.4273. Min Act: -0.0001

Data Index: 1258581 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.7025. Min Act: -0.0001

Data Index: 305084 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5693. Min Act: -0.0001

Data Index: 250243 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.4875. Min Act: -0.0001

Data Index: 768287 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.7085. Min Act: -0.0001

Data Index: 513227 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.4675. Min Act: -0.0001

Data Index: 1225324 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5566. Min Act: -0.0001

Data Index: 988310 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.4716. Min Act: -0.0001

Data Index: 556439 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.4243. Min Act: -0.0001

Data Index: 165246 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 1.8989. Min Range: -1.8989

Max Act: 1.5410. Min Act: -0.0001

Data Index: 68595 (C4 (Web Text))

Max Activating Token Index: 474