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

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

Neuron 1884 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.4151. Min Act: -0.0001

Data Index: 549973 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.2117. Min Act: -0.0001

Data Index: 679918 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.2368. Min Act: -0.0001

Data Index: 665086 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.2249. Min Act: -0.0001

Data Index: 976301 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.1272. Min Act: -0.0001

Data Index: 850495 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.1973. Min Act: -0.0001

Data Index: 27013 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.1430. Min Act: -0.0001

Data Index: 1237482 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.1345. Min Act: -0.0001

Data Index: 775262 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.2135. Min Act: -0.0001

Data Index: 450303 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0797. Min Act: -0.0001

Data Index: 933526 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0315. Min Act: -0.0001

Data Index: 499314 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0877. Min Act: -0.0001

Data Index: 957256 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.1072. Min Act: -0.0001

Data Index: 1305988 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0533. Min Act: -0.0001

Data Index: 900544 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9925. Min Act: -0.0001

Data Index: 389092 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0379. Min Act: -0.0001

Data Index: 577181 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0580. Min Act: -0.0001

Data Index: 471006 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 1.4151. Min Range: -1.4151

Max Act: 0.9829. Min Act: -0.0001

Data Index: 76900 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0427. Min Act: -0.0001

Data Index: 760750 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 1.4151. Min Range: -1.4151

Max Act: 1.0093. Min Act: -0.0001

Data Index: 49919 (C4 (Web Text))

Max Activating Token Index: 801