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

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

Neuron 2556 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: 0.0120. Min Range: -0.0120

Max Act: 0.0120. Min Act: -0.0002

Data Index: 426302 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0116. Min Act: -0.0002

Data Index: 92603 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1600289 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0114. Min Act: -0.0002

Data Index: 643361 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0113. Min Act: -0.0002

Data Index: 632295 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0113. Min Act: -0.0002

Data Index: 524984 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1255354 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0111. Min Act: -0.0002

Data Index: 354640 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1077234 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0110. Min Act: -0.0002

Data Index: 493228 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1570215 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1169953 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1524268 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0109. Min Act: -0.0002

Data Index: 679951 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0109. Min Act: -0.0002

Data Index: 532886 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0109. Min Act: -0.0002

Data Index: 567175 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0108. Min Act: -0.0002

Data Index: 1217390 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0110. Min Act: -0.0002

Data Index: 301648 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0108. Min Act: -0.0002

Data Index: 366139 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0108. Min Act: -0.0002

Data Index: 1503208 (Python Code)

Max Activating Token Index: 17