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

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

Neuron 2734 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.6327. Min Act: -0.0000

Data Index: 1360550 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.5549. Min Act: -0.0001

Data Index: 1507638 (Python Code)

Max Activating Token Index: 671

Text #2

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.3726. Min Act: -0.0000

Data Index: 1471379 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.3479. Min Act: -0.0000

Data Index: 1428252 (Python Code)

Max Activating Token Index: 793

Text #4

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0043. Min Act: -0.0001

Data Index: 1542724 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.2250. Min Act: -0.0000

Data Index: 1598940 (Python Code)

Max Activating Token Index: 321

Text #6

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.2993. Min Act: -0.0000

Data Index: 1630231 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.1337. Min Act: -0.0001

Data Index: 1465896 (Python Code)

Max Activating Token Index: 677

Text #8

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.2211. Min Act: -0.0001

Data Index: 1539316 (Python Code)

Max Activating Token Index: 407

Text #9

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0508. Min Act: -0.0000

Data Index: 1607728 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0280. Min Act: -0.0000

Data Index: 1409239 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 2.6327. Min Range: -2.6327

Max Act: 1.9871. Min Act: -0.0000

Data Index: 1585675 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 2.6327. Min Range: -2.6327

Max Act: 1.9842. Min Act: -0.0000

Data Index: 1460590 (Python Code)

Max Activating Token Index: 350

Text #13

Max Range: 2.6327. Min Range: -2.6327

Max Act: 1.8629. Min Act: -0.0000

Data Index: 1513769 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0677. Min Act: -0.0001

Data Index: 1626367 (Python Code)

Max Activating Token Index: 205

Text #15

Max Range: 2.6327. Min Range: -2.6327

Max Act: 1.9663. Min Act: -0.0000

Data Index: 1606912 (Python Code)

Max Activating Token Index: 593

Text #16

Max Range: 2.6327. Min Range: -2.6327

Max Act: 1.9473. Min Act: -0.0000

Data Index: 1428719 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 2.6327. Min Range: -2.6327

Max Act: 2.0457. Min Act: -0.0001

Data Index: 1493056 (Python Code)

Max Activating Token Index: 557

Text #18

Max Range: 2.6327. Min Range: -2.6327

Max Act: 1.7331. Min Act: -0.0000

Data Index: 1639625 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 2.6327. Min Range: -2.6327

Max Act: 1.9361. Min Act: -0.0000

Data Index: 1468903 (Python Code)

Max Activating Token Index: 432