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

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

Neuron 5118 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0001

Data Index: 1418700 (Python Code)

Max Activating Token Index: 509

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0138. Min Act: -0.0001

Data Index: 1520093 (Python Code)

Max Activating Token Index: 409

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0136. Min Act: -0.0001

Data Index: 1584111 (Python Code)

Max Activating Token Index: 350

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0136. Min Act: -0.0000

Data Index: 1523658 (Python Code)

Max Activating Token Index: 446

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0140. Min Act: -0.0000

Data Index: 1395371 (Python Code)

Max Activating Token Index: 439

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0133. Min Act: -0.0001

Data Index: 1405638 (Python Code)

Max Activating Token Index: 432

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0132. Min Act: -0.0001

Data Index: 1562709 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0137. Min Act: -0.0001

Data Index: 1415350 (Python Code)

Max Activating Token Index: 409

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0000

Data Index: 1362733 (Python Code)

Max Activating Token Index: 515

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1445719 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1587973 (Python Code)

Max Activating Token Index: 386

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0000

Data Index: 1415228 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1437105 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0001

Data Index: 1556116 (Python Code)

Max Activating Token Index: 474

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0000

Data Index: 1422210 (Python Code)

Max Activating Token Index: 416

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0000

Data Index: 1518647 (Python Code)

Max Activating Token Index: 426

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0001

Data Index: 1416906 (Python Code)

Max Activating Token Index: 429

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0001

Data Index: 1489822 (Python Code)

Max Activating Token Index: 410

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0000

Data Index: 1378898 (Python Code)

Max Activating Token Index: 518

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0000

Data Index: 1435761 (Python Code)

Max Activating Token Index: 567