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

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

Neuron 706 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: 3.6394. Min Range: -3.6394

Max Act: 3.6394. Min Act: -0.0001

Data Index: 647105 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.0834. Min Act: -0.0001

Data Index: 360701 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.1674. Min Act: -0.0001

Data Index: 752692 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.0050. Min Act: -0.0001

Data Index: 292811 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.1219. Min Act: -0.0001

Data Index: 1263466 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.9219. Min Act: -0.0001

Data Index: 20023 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.7823. Min Act: -0.0001

Data Index: 533723 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.9937. Min Act: -0.0001

Data Index: 680367 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.8319. Min Act: -0.0001

Data Index: 629601 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.7933. Min Act: -0.0001

Data Index: 52859 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.8109. Min Act: -0.0001

Data Index: 881018 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.7832. Min Act: -0.0001

Data Index: 1096105 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.6338. Min Act: -0.0001

Data Index: 1327074 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.7682. Min Act: -0.0001

Data Index: 955926 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.6105. Min Act: -0.0000

Data Index: 1281585 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.7083. Min Act: -0.0001

Data Index: 374172 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.6890. Min Act: -0.0000

Data Index: 693966 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.8257. Min Act: -0.0001

Data Index: 550325 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.6604. Min Act: -0.0001

Data Index: 655122 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 3.6394. Min Range: -3.6394

Max Act: 2.6571. Min Act: -0.0001

Data Index: 980559 (C4 (Web Text))

Max Activating Token Index: 165