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

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

Neuron 3316 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1401797 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0970. Min Act: -0.0001

Data Index: 292176 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1534621 (Python Code)

Max Activating Token Index: 693

Text #3

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1373311 (Python Code)

Max Activating Token Index: 777

Text #4

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1403280 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1596425 (Python Code)

Max Activating Token Index: 490

Text #6

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1047336 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0791. Min Act: -0.0000

Data Index: 1492287 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1484028 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1605829 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0818. Min Act: -0.0001

Data Index: 884322 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1542254 (Python Code)

Max Activating Token Index: 646

Text #12

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1405189 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1460444 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1310029 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1179725 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1629976 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0849. Min Act: -0.0001

Data Index: 493927 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0818. Min Act: -0.0001

Data Index: 757218 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1600036 (Python Code)

Max Activating Token Index: 554