Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4729 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0109. Min Act: -0.0002

Data Index: 368955 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0108. Min Act: -0.0002

Data Index: 596454 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1256400 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1309058 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0105. Min Act: -0.0002

Data Index: 651497 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1177463 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0104. Min Act: -0.0002

Data Index: 808478 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0103. Min Act: -0.0002

Data Index: 45772 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0103. Min Act: -0.0002

Data Index: 114562 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0101. Min Act: -0.0002

Data Index: 323661 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0101. Min Act: -0.0002

Data Index: 134858 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0002

Data Index: 175395 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0002

Data Index: 908227 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0002

Data Index: 679628 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0002

Data Index: 126257 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0002

Data Index: 457582 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1319955 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0002

Data Index: 18540 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1040839 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0099. Min Act: -0.0002

Data Index: 13672 (C4 (Web Text))

Max Activating Token Index: 55