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

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

Neuron 205 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.7100. Min Act: -0.0002

Data Index: 705172 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.4069. Min Act: -0.0002

Data Index: 1045018 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.3256. Min Act: -0.0002

Data Index: 514929 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.2586. Min Act: -0.0002

Data Index: 257256 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.1792. Min Act: -0.0002

Data Index: 1027173 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.2915. Min Act: -0.0002

Data Index: 292289 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.1585. Min Act: -0.0002

Data Index: 1140518 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.2567. Min Act: -0.0002

Data Index: 762280 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.1837. Min Act: -0.0002

Data Index: 1333274 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.1781. Min Act: -0.0002

Data Index: 138356 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.1892. Min Act: -0.0002

Data Index: 1165762 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.0413. Min Act: -0.0002

Data Index: 841966 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.0756. Min Act: -0.0002

Data Index: 88852 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.1715. Min Act: -0.0002

Data Index: 673158 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.1093. Min Act: -0.0002

Data Index: 1344375 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.0945. Min Act: -0.0002

Data Index: 217414 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.0318. Min Act: -0.0002

Data Index: 1168988 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.1457. Min Act: -0.0002

Data Index: 144315 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.0452. Min Act: -0.0002

Data Index: 514539 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.7100. Min Range: -1.7100

Max Act: 1.0140. Min Act: -0.0002

Data Index: 624067 (C4 (Web Text))

Max Activating Token Index: 63