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

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

Neuron 5074 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: 0.0123. Min Range: -0.0123

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1811 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0123. Min Act: -0.0002

Data Index: 950101 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1112690 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1333269 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0118. Min Act: -0.0002

Data Index: 562919 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0117. Min Act: -0.0002

Data Index: 476164 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0114. Min Act: -0.0002

Data Index: 348209 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0111. Min Act: -0.0002

Data Index: 776423 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1123272 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1278790 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0111. Min Act: -0.0002

Data Index: 899861 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0109. Min Act: -0.0002

Data Index: 772827 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0108. Min Act: -0.0002

Data Index: 670858 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0108. Min Act: -0.0002

Data Index: 879882 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0107. Min Act: -0.0002

Data Index: 336020 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1116559 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0106. Min Act: -0.0002

Data Index: 602663 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0106. Min Act: -0.0002

Data Index: 17751 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0105. Min Act: -0.0002

Data Index: 947085 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0105. Min Act: -0.0002

Data Index: 2092 (C4 (Web Text))

Max Activating Token Index: 89