Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 196 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4628. Min Act: -0.0003

Data Index: 1359590 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3564. Min Act: -0.0003

Data Index: 361417 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2755. Min Act: -0.0003

Data Index: 119231 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3343. Min Act: -0.0003

Data Index: 66545 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1709. Min Act: -0.0003

Data Index: 990688 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2502. Min Act: -0.0003

Data Index: 441753 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1377. Min Act: -0.0003

Data Index: 921892 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.0277. Min Act: -0.0003

Data Index: 1357534 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.0138. Min Act: -0.0003

Data Index: 687815 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2479. Min Act: -0.0003

Data Index: 862939 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1503. Min Act: -0.0003

Data Index: 557416 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1251. Min Act: -0.0003

Data Index: 386902 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1272. Min Act: -0.0003

Data Index: 287564 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1940. Min Act: -0.0003

Data Index: 815240 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1977. Min Act: -0.0003

Data Index: 1070076 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.0754. Min Act: -0.0003

Data Index: 387918 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1512. Min Act: -0.0003

Data Index: 924760 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.2206. Min Act: -0.0003

Data Index: 55831 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1438. Min Act: -0.0003

Data Index: 277150 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.1752. Min Act: -0.0003

Data Index: 252692 (C4 (Web Text))

Max Activating Token Index: 437