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

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

Neuron 2204 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0002

Data Index: 10519 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1227512 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0499. Min Act: -0.0002

Data Index: 489732 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0466. Min Act: -0.0002

Data Index: 453423 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0489. Min Act: -0.0002

Data Index: 423785 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1066952 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0417. Min Act: -0.0002

Data Index: 138640 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0426. Min Act: -0.0002

Data Index: 275688 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0456. Min Act: -0.0002

Data Index: 155716 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1149843 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0451. Min Act: -0.0002

Data Index: 938464 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1205919 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0382. Min Act: -0.0002

Data Index: 334588 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1012098 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0429. Min Act: -0.0002

Data Index: 867882 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0430. Min Act: -0.0002

Data Index: 239883 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0427. Min Act: -0.0002

Data Index: 705823 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0419. Min Act: -0.0002

Data Index: 302265 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0437. Min Act: -0.0002

Data Index: 215741 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0413. Min Act: -0.0002

Data Index: 931795 (C4 (Web Text))

Max Activating Token Index: 981