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

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

Neuron 1704 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0002

Data Index: 754272 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0459. Min Act: -0.0002

Data Index: 429968 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0422. Min Act: -0.0003

Data Index: 169597 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0372. Min Act: -0.0003

Data Index: 859494 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1168998 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0399. Min Act: -0.0003

Data Index: 906437 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0406. Min Act: -0.0003

Data Index: 419277 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0396. Min Act: -0.0003

Data Index: 967619 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0394. Min Act: -0.0002

Data Index: 723453 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1071086 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1013105 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0404. Min Act: -0.0003

Data Index: 603018 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0385. Min Act: -0.0002

Data Index: 742264 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1145413 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1195331 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0381. Min Act: -0.0003

Data Index: 957007 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1271320 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0362. Min Act: -0.0002

Data Index: 789927 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0367. Min Act: -0.0003

Data Index: 866586 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0348. Min Act: -0.0002

Data Index: 873177 (C4 (Web Text))

Max Activating Token Index: 156