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

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

Neuron 496 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.8790. Min Act: -0.0000

Data Index: 785087 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.9188. Min Act: -0.0000

Data Index: 207591 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 3.0045. Min Range: -3.0045

Max Act: 3.0045. Min Act: -0.0000

Data Index: 67014 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.5159. Min Act: -0.0000

Data Index: 668046 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.5348. Min Act: -0.0000

Data Index: 224383 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.3474. Min Act: -0.0000

Data Index: 882420 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.4048. Min Act: -0.0000

Data Index: 417447 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.2285. Min Act: -0.0000

Data Index: 105711 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.2680. Min Act: -0.0000

Data Index: 443232 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.3044. Min Act: -0.0000

Data Index: 1140811 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.3135. Min Act: -0.0000

Data Index: 97882 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.3267. Min Act: -0.0000

Data Index: 613423 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.3617. Min Act: -0.0000

Data Index: 670544 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.1362. Min Act: -0.0000

Data Index: 606039 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.1724. Min Act: -0.0000

Data Index: 317226 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.2187. Min Act: -0.0000

Data Index: 1039381 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.1931. Min Act: -0.0000

Data Index: 293744 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.1723. Min Act: -0.0000

Data Index: 902161 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.2278. Min Act: -0.0000

Data Index: 1294413 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 3.0045. Min Range: -3.0045

Max Act: 2.1637. Min Act: -0.0000

Data Index: 1092438 (C4 (Web Text))

Max Activating Token Index: 265