Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 663 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0565. Min Act: -0.0005

Data Index: 1036772 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0491. Min Act: -0.0005

Data Index: 657363 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0481. Min Act: -0.0005

Data Index: 463832 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0479. Min Act: -0.0005

Data Index: 28547 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0452. Min Act: -0.0005

Data Index: 1149823 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0475. Min Act: -0.0005

Data Index: 510527 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0460. Min Act: -0.0005

Data Index: 991285 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0452. Min Act: -0.0005

Data Index: 562484 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0457. Min Act: -0.0005

Data Index: 221706 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0473. Min Act: -0.0005

Data Index: 1217908 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0440. Min Act: -0.0005

Data Index: 1183967 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0414. Min Act: -0.0005

Data Index: 395001 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0428. Min Act: -0.0005

Data Index: 287344 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0427. Min Act: -0.0005

Data Index: 370332 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0439. Min Act: -0.0005

Data Index: 1109964 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0415. Min Act: -0.0005

Data Index: 310346 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0412. Min Act: -0.0005

Data Index: 1158103 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0420. Min Act: -0.0005

Data Index: 640045 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0412. Min Act: -0.0005

Data Index: 296429 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0427. Min Act: -0.0005

Data Index: 6993 (C4 (Web Text))

Max Activating Token Index: 108