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

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

Neuron 3030 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.9366. Min Act: -0.0002

Data Index: 1341581 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.8699. Min Act: -0.0001

Data Index: 1356601 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.8112. Min Act: -0.0001

Data Index: 872217 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.8179. Min Act: -0.0001

Data Index: 280620 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.8037. Min Act: -0.0002

Data Index: 617879 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.7244. Min Act: -0.0001

Data Index: 737016 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.6375. Min Act: -0.0001

Data Index: 759305 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.6953. Min Act: -0.0001

Data Index: 741298 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.6935. Min Act: -0.0001

Data Index: 1150290 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.6337. Min Act: -0.0001

Data Index: 716965 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.5047. Min Act: -0.0001

Data Index: 1324330 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.6032. Min Act: -0.0002

Data Index: 619141 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.5580. Min Act: -0.0001

Data Index: 156810 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.5135. Min Act: -0.0002

Data Index: 128239 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.5726. Min Act: -0.0001

Data Index: 659381 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.6785. Min Act: -0.0001

Data Index: 236140 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.5343. Min Act: -0.0001

Data Index: 1166246 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.5765. Min Act: -0.0002

Data Index: 722049 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.6227. Min Act: -0.0002

Data Index: 1076770 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 1.9366. Min Range: -1.9366

Max Act: 1.6068. Min Act: -0.0001

Data Index: 732786 (C4 (Web Text))

Max Activating Token Index: 349