Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 449 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0192. Min Act: -0.0003

Data Index: 28587 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1229783 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1034570 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0140. Min Act: -0.0003

Data Index: 972832 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0142. Min Act: -0.0003

Data Index: 796374 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1107667 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1107722 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0129. Min Act: -0.0003

Data Index: 23620 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1015760 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0129. Min Act: -0.0002

Data Index: 904500 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0137. Min Act: -0.0002

Data Index: 610844 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1015233 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1306528 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0128. Min Act: -0.0003

Data Index: 397452 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1067935 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0125. Min Act: -0.0003

Data Index: 400490 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1113455 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0128. Min Act: -0.0003

Data Index: 528414 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0117. Min Act: -0.0002

Data Index: 622686 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0117. Min Act: -0.0003

Data Index: 564203 (C4 (Web Text))

Max Activating Token Index: 180