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

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

Neuron 468 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2348. Min Act: -0.0003

Data Index: 36559 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1932. Min Act: -0.0003

Data Index: 335670 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.2050. Min Act: -0.0003

Data Index: 659919 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1712. Min Act: -0.0003

Data Index: 525350 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1678. Min Act: -0.0003

Data Index: 104095 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1664. Min Act: -0.0003

Data Index: 779350 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1705. Min Act: -0.0003

Data Index: 673184 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1690. Min Act: -0.0003

Data Index: 648891 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1696. Min Act: -0.0002

Data Index: 679169 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1703. Min Act: -0.0003

Data Index: 1182100 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1677. Min Act: -0.0003

Data Index: 1186393 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1645. Min Act: -0.0003

Data Index: 1010166 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1591. Min Act: -0.0002

Data Index: 250760 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1632. Min Act: -0.0003

Data Index: 102116 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1557. Min Act: -0.0003

Data Index: 772019 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1555. Min Act: -0.0003

Data Index: 1032545 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1505. Min Act: -0.0002

Data Index: 372515 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1443. Min Act: -0.0003

Data Index: 1326586 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1421. Min Act: -0.0003

Data Index: 364203 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.2348. Min Range: -0.2348

Max Act: 0.1480. Min Act: -0.0003

Data Index: 247857 (C4 (Web Text))

Max Activating Token Index: 771