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

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

Neuron 2455 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: 0.0109. Min Range: -0.0109

Max Act: 0.0108. Min Act: -0.0003

Data Index: 524863 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1009270 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0108. Min Act: -0.0003

Data Index: 254053 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0107. Min Act: -0.0003

Data Index: 123997 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1088803 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0108. Min Act: -0.0004

Data Index: 240796 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0108. Min Act: -0.0003

Data Index: 740912 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1101604 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0104. Min Act: -0.0003

Data Index: 676111 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1094586 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0106. Min Act: -0.0004

Data Index: 941504 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0106. Min Act: -0.0004

Data Index: 904941 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0105. Min Act: -0.0004

Data Index: 1145096 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0105. Min Act: -0.0004

Data Index: 173885 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0103. Min Act: -0.0003

Data Index: 270768 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0105. Min Act: -0.0004

Data Index: 232604 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0102. Min Act: -0.0004

Data Index: 892593 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1312962 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0102. Min Act: -0.0004

Data Index: 255521 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0104. Min Act: -0.0003

Data Index: 354629 (C4 (Web Text))

Max Activating Token Index: 559