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

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

Neuron 632 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0005

Data Index: 609517 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0141. Min Act: -0.0005

Data Index: 1213534 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0140. Min Act: -0.0006

Data Index: 563145 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0136. Min Act: -0.0006

Data Index: 189231 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0128. Min Act: -0.0006

Data Index: 379891 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0131. Min Act: -0.0006

Data Index: 303246 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0006

Data Index: 261594 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0005

Data Index: 857560 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1438936 (Python Code)

Max Activating Token Index: 620

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1554379 (Python Code)

Max Activating Token Index: 295

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1570787 (Python Code)

Max Activating Token Index: 760

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0006

Data Index: 619952 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1434693 (Python Code)

Max Activating Token Index: 542

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1454893 (Python Code)

Max Activating Token Index: 442

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0006

Data Index: 723631 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1409730 (Python Code)

Max Activating Token Index: 433

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1607846 (Python Code)

Max Activating Token Index: 385

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1444081 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0119. Min Act: -0.0006

Data Index: 49898 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1570496 (Python Code)

Max Activating Token Index: 383