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

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

Neuron 1840 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0107. Min Act: -0.0004

Data Index: 30239 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0078. Min Act: -0.0003

Data Index: 840786 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0074. Min Act: -0.0004

Data Index: 579518 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1116629 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0073. Min Act: -0.0003

Data Index: 57683 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0071. Min Act: -0.0004

Data Index: 702059 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0069. Min Act: -0.0003

Data Index: 879533 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0070. Min Act: -0.0003

Data Index: 809079 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0068. Min Act: -0.0003

Data Index: 928126 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0067. Min Act: -0.0003

Data Index: 867498 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0067. Min Act: -0.0003

Data Index: 856464 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1193769 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0065. Min Act: -0.0004

Data Index: 498540 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0065. Min Act: -0.0003

Data Index: 688289 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1160676 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0063. Min Act: -0.0003

Data Index: 334759 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0063. Min Act: -0.0004

Data Index: 463336 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0064. Min Act: -0.0003

Data Index: 523272 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1279981 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0064. Min Act: -0.0004

Data Index: 668790 (C4 (Web Text))

Max Activating Token Index: 233