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

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

Neuron 910 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0109. Min Act: -0.0006

Data Index: 294 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1271412 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0102. Min Act: -0.0006

Data Index: 282678 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1084897 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1354718 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0101. Min Act: -0.0005

Data Index: 663427 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0103. Min Act: -0.0006

Data Index: 559885 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0102. Min Act: -0.0006

Data Index: 391125 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0006

Data Index: 360312 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1070167 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0099. Min Act: -0.0006

Data Index: 149296 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1321190 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0095. Min Act: -0.0006

Data Index: 666292 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0098. Min Act: -0.0006

Data Index: 230434 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0098. Min Act: -0.0006

Data Index: 686935 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0096. Min Act: -0.0006

Data Index: 832292 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0093. Min Act: -0.0005

Data Index: 1473777 (Python Code)

Max Activating Token Index: 183

Text #17

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0095. Min Act: -0.0006

Data Index: 859768 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0095. Min Act: -0.0006

Data Index: 103094 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0094. Min Act: -0.0006

Data Index: 611052 (C4 (Web Text))

Max Activating Token Index: 672