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

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

Neuron 3081 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.5286. Min Act: -0.0000

Data Index: 510898 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.5054. Min Act: -0.0000

Data Index: 314110 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1267859 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4553. Min Act: -0.0000

Data Index: 936520 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4521. Min Act: -0.0000

Data Index: 304845 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1274760 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1279268 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4155. Min Act: -0.0000

Data Index: 997039 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4085. Min Act: -0.0000

Data Index: 537841 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4095. Min Act: -0.0000

Data Index: 111860 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4327. Min Act: -0.0000

Data Index: 434963 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4023. Min Act: -0.0000

Data Index: 841422 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4010. Min Act: -0.0000

Data Index: 218827 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1351442 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1071583 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3981. Min Act: -0.0000

Data Index: 397341 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3989. Min Act: -0.0000

Data Index: 355182 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3961. Min Act: -0.0000

Data Index: 480725 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3817. Min Act: -0.0000

Data Index: 272687 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1280761 (C4 (Web Text))

Max Activating Token Index: 771