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

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

Neuron 864 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1493674 (Python Code)

Max Activating Token Index: 799

Text #1

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1570687 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.3132. Min Act: -0.0000

Data Index: 683829 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.3255. Min Act: -0.0000

Data Index: 24474 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.3405. Min Act: -0.0000

Data Index: 371808 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2987. Min Act: -0.0000

Data Index: 516655 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.3126. Min Act: -0.0000

Data Index: 621355 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1521659 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2779. Min Act: -0.0000

Data Index: 179323 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2981. Min Act: -0.0000

Data Index: 799530 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.3058. Min Act: -0.0000

Data Index: 652195 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2761. Min Act: -0.0000

Data Index: 807945 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2668. Min Act: -0.0000

Data Index: 182665 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1558246 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2710. Min Act: -0.0000

Data Index: 547586 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1403146 (Python Code)

Max Activating Token Index: 931

Text #16

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2562. Min Act: -0.0000

Data Index: 127641 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2526. Min Act: -0.0000

Data Index: 667653 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2510. Min Act: -0.0000

Data Index: 240624 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.4175. Min Range: -0.4175

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1620147 (Python Code)

Max Activating Token Index: 92