Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 737 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0002

Data Index: 115972 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0127. Min Act: -0.0001

Data Index: 363359 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0109. Min Act: -0.0002

Data Index: 600672 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0101. Min Act: -0.0002

Data Index: 1609877 (Python Code)

Max Activating Token Index: 974

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0124. Min Act: -0.0002

Data Index: 665602 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0123. Min Act: -0.0002

Data Index: 742262 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0097. Min Act: -0.0001

Data Index: 324848 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0102. Min Act: -0.0002

Data Index: 571360 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0109. Min Act: -0.0002

Data Index: 398884 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0098. Min Act: -0.0002

Data Index: 549582 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1076748 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0124. Min Act: -0.0002

Data Index: 850169 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0107. Min Act: -0.0002

Data Index: 169676 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0092. Min Act: -0.0002

Data Index: 83853 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0104. Min Act: -0.0002

Data Index: 629534 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0099. Min Act: -0.0002

Data Index: 584015 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0053. Min Act: -0.0002

Data Index: 701204 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0081. Min Act: -0.0002

Data Index: 365654 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1301971 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0102. Min Act: -0.0001

Data Index: 355593 (C4 (Web Text))

Max Activating Token Index: 456