Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 984 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0006

Data Index: 192667 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1044293 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0006

Data Index: 390669 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0006

Data Index: 262656 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0119. Min Act: -0.0006

Data Index: 167226 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1229136 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0116. Min Act: -0.0006

Data Index: 744679 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1269736 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1356619 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0113. Min Act: -0.0006

Data Index: 815597 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0110. Min Act: -0.0006

Data Index: 833562 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0110. Min Act: -0.0006

Data Index: 402500 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0109. Min Act: -0.0006

Data Index: 918232 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0109. Min Act: -0.0005

Data Index: 600181 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1010372 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0108. Min Act: -0.0006

Data Index: 189532 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0106. Min Act: -0.0005

Data Index: 40309 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0107. Min Act: -0.0006

Data Index: 63498 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1354790 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0107. Min Act: -0.0006

Data Index: 102387 (C4 (Web Text))

Max Activating Token Index: 530