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

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

Neuron 4078 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1545492 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1571196 (Python Code)

Max Activating Token Index: 257

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1536887 (Python Code)

Max Activating Token Index: 619

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1605447 (Python Code)

Max Activating Token Index: 298

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1550655 (Python Code)

Max Activating Token Index: 831

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1415068 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1435464 (Python Code)

Max Activating Token Index: 720

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1484603 (Python Code)

Max Activating Token Index: 454

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1359922 (Python Code)

Max Activating Token Index: 456

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1606584 (Python Code)

Max Activating Token Index: 570

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1480366 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1515706 (Python Code)

Max Activating Token Index: 215

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1625033 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1462089 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1640862 (Python Code)

Max Activating Token Index: 332

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1632067 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1578145 (Python Code)

Max Activating Token Index: 675

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1568145 (Python Code)

Max Activating Token Index: 141

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1594485 (Python Code)

Max Activating Token Index: 562

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1388524 (Python Code)

Max Activating Token Index: 66