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

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

Neuron 5067 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.9457. Min Act: -0.0000

Data Index: 1576369 (Python Code)

Max Activating Token Index: 576

Text #1

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1476753 (Python Code)

Max Activating Token Index: 264

Text #2

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1457571 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1478676 (Python Code)

Max Activating Token Index: 314

Text #4

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1503226 (Python Code)

Max Activating Token Index: 359

Text #5

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1507977 (Python Code)

Max Activating Token Index: 389

Text #6

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1521041 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1620156 (Python Code)

Max Activating Token Index: 539

Text #8

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1373072 (Python Code)

Max Activating Token Index: 862

Text #9

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1612943 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1491638 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1403657 (Python Code)

Max Activating Token Index: 607

Text #12

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1502627 (Python Code)

Max Activating Token Index: 238

Text #13

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1372778 (Python Code)

Max Activating Token Index: 558

Text #14

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1415190 (Python Code)

Max Activating Token Index: 714

Text #15

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1630680 (Python Code)

Max Activating Token Index: 724

Text #16

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1392850 (Python Code)

Max Activating Token Index: 931

Text #17

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1535376 (Python Code)

Max Activating Token Index: 846

Text #18

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1633262 (Python Code)

Max Activating Token Index: 811

Text #19

Max Range: 0.9457. Min Range: -0.9457

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1397643 (Python Code)

Max Activating Token Index: 682