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

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

Neuron 1034 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0150. Min Act: -0.0006

Data Index: 272063 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0151. Min Act: -0.0006

Data Index: 937519 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0138. Min Act: -0.0006

Data Index: 582348 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0140. Min Act: -0.0006

Data Index: 723167 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0136. Min Act: -0.0006

Data Index: 620784 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0132. Min Act: -0.0006

Data Index: 555380 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1217405 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1122413 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0124. Min Act: -0.0006

Data Index: 280487 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1100779 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0124. Min Act: -0.0006

Data Index: 27546 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0126. Min Act: -0.0006

Data Index: 218515 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0124. Min Act: -0.0006

Data Index: 789867 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1338679 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0125. Min Act: -0.0006

Data Index: 903293 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0124. Min Act: -0.0006

Data Index: 363791 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0120. Min Act: -0.0006

Data Index: 949452 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0120. Min Act: -0.0006

Data Index: 820084 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0120. Min Act: -0.0006

Data Index: 336340 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0117. Min Act: -0.0006

Data Index: 686775 (C4 (Web Text))

Max Activating Token Index: 574