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

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

Neuron 477 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: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0006

Data Index: 414271 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0124. Min Act: -0.0006

Data Index: 449477 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0120. Min Act: -0.0006

Data Index: 798411 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0118. Min Act: -0.0006

Data Index: 597129 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0117. Min Act: -0.0006

Data Index: 458223 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0117. Min Act: -0.0006

Data Index: 314265 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0006

Data Index: 247849 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1287995 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0116. Min Act: -0.0006

Data Index: 185436 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0006

Data Index: 95479 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0006

Data Index: 128668 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0006

Data Index: 334566 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1038575 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0006

Data Index: 58660 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1252411 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1054759 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1221459 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1021673 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1236309 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0006

Data Index: 814248 (C4 (Web Text))

Max Activating Token Index: 595