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

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

Neuron 8 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.9964. Min Act: -0.0001

Data Index: 1281570 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 4.1558. Min Range: -4.1558

Max Act: 4.1027. Min Act: -0.0001

Data Index: 860425 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.9424. Min Act: -0.0001

Data Index: 691208 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 4.1558. Min Range: -4.1558

Max Act: 4.1558. Min Act: -0.0001

Data Index: 119191 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.6017. Min Act: -0.0001

Data Index: 879952 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.5483. Min Act: -0.0001

Data Index: 925630 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.2129. Min Act: -0.0001

Data Index: 925590 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.1480. Min Act: -0.0001

Data Index: 612894 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.0891. Min Act: -0.0001

Data Index: 636462 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.3453. Min Act: -0.0001

Data Index: 15062 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.1017. Min Act: -0.0001

Data Index: 953342 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 4.1558. Min Range: -4.1558

Max Act: 2.9893. Min Act: -0.0001

Data Index: 339988 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 4.1558. Min Range: -4.1558

Max Act: 3.1185. Min Act: -0.0001

Data Index: 847413 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 4.1558. Min Range: -4.1558

Max Act: 2.9412. Min Act: -0.0001

Data Index: 291434 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 4.1558. Min Range: -4.1558

Max Act: 2.8763. Min Act: -0.0001

Data Index: 578253 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 4.1558. Min Range: -4.1558

Max Act: 2.9771. Min Act: -0.0001

Data Index: 1134177 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 4.1558. Min Range: -4.1558

Max Act: 2.8248. Min Act: -0.0001

Data Index: 180686 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 4.1558. Min Range: -4.1558

Max Act: 2.9625. Min Act: -0.0001

Data Index: 380495 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 4.1558. Min Range: -4.1558

Max Act: 2.8300. Min Act: -0.0001

Data Index: 1306953 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 4.1558. Min Range: -4.1558

Max Act: 2.9285. Min Act: -0.0001

Data Index: 810181 (C4 (Web Text))

Max Activating Token Index: 236