Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 980 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0002

Data Index: 164599 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0148. Min Act: -0.0002

Data Index: 880517 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1356444 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0144. Min Act: -0.0002

Data Index: 464266 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1347289 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1204328 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0130. Min Act: -0.0002

Data Index: 26972 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1223644 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0125. Min Act: -0.0002

Data Index: 446751 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0117. Min Act: -0.0002

Data Index: 497729 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0126. Min Act: -0.0002

Data Index: 170646 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0002

Data Index: 71754 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0109. Min Act: -0.0002

Data Index: 822850 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0112. Min Act: -0.0002

Data Index: 303341 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1450254 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0118. Min Act: -0.0002

Data Index: 114617 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0111. Min Act: -0.0002

Data Index: 301316 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0106. Min Act: -0.0002

Data Index: 263274 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0110. Min Act: -0.0002

Data Index: 569042 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1190344 (C4 (Web Text))

Max Activating Token Index: 717