Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 398 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0151. Min Act: -0.0004

Data Index: 877258 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0127. Min Act: -0.0003

Data Index: 652860 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0121. Min Act: -0.0003

Data Index: 777406 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0116. Min Act: -0.0003

Data Index: 712238 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0116. Min Act: -0.0003

Data Index: 119298 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0115. Min Act: -0.0004

Data Index: 362622 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0110. Min Act: -0.0003

Data Index: 1520651 (Python Code)

Max Activating Token Index: 316

Text #7

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0110. Min Act: -0.0003

Data Index: 954847 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0107. Min Act: -0.0003

Data Index: 689976 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1228170 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1558463 (Python Code)

Max Activating Token Index: 264

Text #11

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1599058 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1587273 (Python Code)

Max Activating Token Index: 324

Text #13

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0106. Min Act: -0.0003

Data Index: 905187 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1012980 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0103. Min Act: -0.0003

Data Index: 628490 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1006646 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0104. Min Act: -0.0003

Data Index: 829415 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0104. Min Act: -0.0002

Data Index: 984018 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1498421 (Python Code)

Max Activating Token Index: 414