Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 196 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1378741 (Python Code)

Max Activating Token Index: 990

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0136. Min Act: -0.0003

Data Index: 270729 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0132. Min Act: -0.0003

Data Index: 446896 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1348285 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0131. Min Act: -0.0003

Data Index: 26808 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0003

Data Index: 981528 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0003

Data Index: 57163 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0003

Data Index: 33895 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1163570 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0003

Data Index: 528815 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1362416 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0003

Data Index: 824208 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1446346 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1380782 (Python Code)

Max Activating Token Index: 736

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0003

Data Index: 966737 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0113. Min Act: -0.0003

Data Index: 1546915 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0116. Min Act: -0.0003

Data Index: 349810 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1372328 (Python Code)

Max Activating Token Index: 133

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0107. Min Act: -0.0004

Data Index: 621001 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0110. Min Act: -0.0003

Data Index: 1617262 (Python Code)

Max Activating Token Index: 1013