Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 981 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1308. Min Act: -0.0002

Data Index: 50416 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1286. Min Act: 0.0001

Data Index: 1094316 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1109. Min Act: -0.0002

Data Index: 382515 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1096. Min Act: -0.0002

Data Index: 451764 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1066. Min Act: -0.0001

Data Index: 967269 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1027. Min Act: -0.0002

Data Index: 965662 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0967. Min Act: -0.0002

Data Index: 411467 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1201225 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0964. Min Act: -0.0002

Data Index: 333927 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1054223 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0928. Min Act: -0.0002

Data Index: 873287 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0902. Min Act: -0.0002

Data Index: 553932 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0905. Min Act: -0.0001

Data Index: 392127 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0886. Min Act: -0.0002

Data Index: 645471 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0893. Min Act: -0.0000

Data Index: 158087 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0894. Min Act: -0.0000

Data Index: 80449 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1195299 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0876. Min Act: -0.0002

Data Index: 16595 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0917. Min Act: -0.0002

Data Index: 496961 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0938. Min Act: -0.0002

Data Index: 69643 (C4 (Web Text))

Max Activating Token Index: 710