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

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

Neuron 1517 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: 0.0470. Min Range: -0.0470

Max Act: 0.0466. Min Act: -0.0002

Data Index: 998744 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0002

Data Index: 832253 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0414. Min Act: -0.0002

Data Index: 979655 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1419560 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1466476 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1441791 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1539565 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0422. Min Act: -0.0002

Data Index: 962142 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0420. Min Act: -0.0002

Data Index: 254870 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1378914 (Python Code)

Max Activating Token Index: 128

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1358346 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1639775 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1384765 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1594500 (Python Code)

Max Activating Token Index: 351

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1453900 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1458152 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1553690 (Python Code)

Max Activating Token Index: 251

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1449958 (Python Code)

Max Activating Token Index: 180

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1392562 (Python Code)

Max Activating Token Index: 126

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0383. Min Act: -0.0002

Data Index: 967779 (C4 (Web Text))

Max Activating Token Index: 279