Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 163 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0006

Data Index: 835331 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1329291 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1338488 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0123. Min Act: -0.0006

Data Index: 132720 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1254574 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0123. Min Act: -0.0006

Data Index: 156588 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0111. Min Act: -0.0006

Data Index: 182302 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0116. Min Act: -0.0006

Data Index: 87483 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0115. Min Act: -0.0006

Data Index: 71639 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0111. Min Act: -0.0006

Data Index: 766686 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0112. Min Act: -0.0006

Data Index: 139315 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0115. Min Act: -0.0006

Data Index: 342242 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1104948 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0113. Min Act: -0.0006

Data Index: 797413 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0115. Min Act: -0.0006

Data Index: 809135 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0114. Min Act: -0.0006

Data Index: 425095 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0104. Min Act: -0.0006

Data Index: 189325 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1260197 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0113. Min Act: -0.0006

Data Index: 749131 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0112. Min Act: -0.0006

Data Index: 999213 (C4 (Web Text))

Max Activating Token Index: 30