Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 936 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0006

Data Index: 204926 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0132. Min Act: -0.0006

Data Index: 165740 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0006

Data Index: 165730 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1044735 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0006

Data Index: 936875 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1502213 (Python Code)

Max Activating Token Index: 898

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0114. Min Act: -0.0006

Data Index: 975463 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1462482 (Python Code)

Max Activating Token Index: 350

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1531545 (Python Code)

Max Activating Token Index: 1019

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0106. Min Act: -0.0006

Data Index: 688853 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0102. Min Act: -0.0006

Data Index: 681779 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1162605 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1522617 (Python Code)

Max Activating Token Index: 945

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0108. Min Act: -0.0006

Data Index: 533565 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0101. Min Act: -0.0006

Data Index: 329250 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1301535 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0101. Min Act: -0.0006

Data Index: 672838 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0105. Min Act: -0.0005

Data Index: 1319231 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0108. Min Act: -0.0005

Data Index: 599076 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0104. Min Act: -0.0006

Data Index: 97041 (C4 (Web Text))

Max Activating Token Index: 464