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

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

Neuron 1792 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: -0.0007

Data Index: 1189780 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0122. Min Act: -0.0006

Data Index: 761835 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0118. Min Act: -0.0006

Data Index: 246413 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0006

Data Index: 441820 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1112946 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0005

Data Index: 668034 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0006

Data Index: 63678 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0112. Min Act: -0.0007

Data Index: 393171 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1502351 (Python Code)

Max Activating Token Index: 331

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0112. Min Act: -0.0006

Data Index: 454163 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0112. Min Act: -0.0006

Data Index: 843132 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0006

Data Index: 634935 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0110. Min Act: -0.0006

Data Index: 498779 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0006

Data Index: 491489 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1493596 (Python Code)

Max Activating Token Index: 222

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0006

Data Index: 860742 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0006

Data Index: 627403 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0006

Data Index: 505372 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0104. Min Act: -0.0006

Data Index: 471736 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1477533 (Python Code)

Max Activating Token Index: 601