Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1944 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0713. Min Act: -0.0002

Data Index: 489772 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0699. Min Act: -0.0001

Data Index: 522449 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0550. Min Act: -0.0001

Data Index: 356120 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0544. Min Act: -0.0002

Data Index: 12766 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1315145 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1111620 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0539. Min Act: -0.0001

Data Index: 256840 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1122393 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1309002 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0487. Min Act: -0.0002

Data Index: 239902 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0436. Min Act: -0.0002

Data Index: 154769 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1181727 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0439. Min Act: -0.0001

Data Index: 548924 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0434. Min Act: -0.0002

Data Index: 590395 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0450. Min Act: -0.0002

Data Index: 324984 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0426. Min Act: -0.0002

Data Index: 179799 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1256568 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0408. Min Act: -0.0001

Data Index: 841355 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0447. Min Act: -0.0002

Data Index: 150567 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0446. Min Act: -0.0001

Data Index: 860678 (C4 (Web Text))

Max Activating Token Index: 49