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

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

Neuron 706 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: 1084710 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0105. Min Act: -0.0006

Data Index: 683643 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0006

Data Index: 835004 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0097. Min Act: -0.0006

Data Index: 473712 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0097. Min Act: -0.0006

Data Index: 464574 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0096. Min Act: -0.0006

Data Index: 197910 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0097. Min Act: -0.0006

Data Index: 142186 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1270719 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0094. Min Act: -0.0006

Data Index: 574336 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1359202 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0095. Min Act: -0.0006

Data Index: 778502 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0095. Min Act: -0.0005

Data Index: 1614180 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1450363 (Python Code)

Max Activating Token Index: 919

Text #13

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0090. Min Act: -0.0006

Data Index: 840067 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1139405 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1068964 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0093. Min Act: -0.0006

Data Index: 687428 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0091. Min Act: -0.0006

Data Index: 723347 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1524698 (Python Code)

Max Activating Token Index: 413

Text #19

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0091. Min Act: -0.0006

Data Index: 376750 (C4 (Web Text))

Max Activating Token Index: 579