Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3927 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1062994 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1063335 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0446. Min Act: -0.0001

Data Index: 817888 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0482. Min Act: -0.0001

Data Index: 185073 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1158911 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0442. Min Act: -0.0001

Data Index: 87097 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0440. Min Act: -0.0001

Data Index: 867374 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0509. Min Act: -0.0001

Data Index: 762771 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0437. Min Act: -0.0001

Data Index: 967674 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0437. Min Act: -0.0001

Data Index: 805595 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1016118 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0509. Min Act: -0.0001

Data Index: 431740 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0443. Min Act: -0.0001

Data Index: 204855 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1277614 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1211545 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1021191 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0412. Min Act: -0.0001

Data Index: 883896 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0444. Min Act: -0.0001

Data Index: 835883 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0429. Min Act: -0.0001

Data Index: 496421 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1014183 (C4 (Web Text))

Max Activating Token Index: 182