Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3638 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.2026. Min Act: -0.0001

Data Index: 1553669 (Python Code)

Max Activating Token Index: 152

Text #1

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1533407 (Python Code)

Max Activating Token Index: 162

Text #2

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1536911 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1881. Min Act: -0.0001

Data Index: 1545732 (Python Code)

Max Activating Token Index: 814

Text #4

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1752. Min Act: -0.0001

Data Index: 1549560 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1368543 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1575919 (Python Code)

Max Activating Token Index: 254

Text #7

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1528730 (Python Code)

Max Activating Token Index: 104

Text #8

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1582. Min Act: -0.0001

Data Index: 1458355 (Python Code)

Max Activating Token Index: 448

Text #9

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1805. Min Act: -0.0001

Data Index: 1642921 (Python Code)

Max Activating Token Index: 933

Text #10

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1550850 (Python Code)

Max Activating Token Index: 197

Text #11

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1545314 (Python Code)

Max Activating Token Index: 794

Text #12

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1547. Min Act: -0.0001

Data Index: 1455138 (Python Code)

Max Activating Token Index: 248

Text #13

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1375238 (Python Code)

Max Activating Token Index: 149

Text #14

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1584502 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1650738 (Python Code)

Max Activating Token Index: 130

Text #16

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1597990 (Python Code)

Max Activating Token Index: 559

Text #17

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1507047 (Python Code)

Max Activating Token Index: 704

Text #18

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1515. Min Act: -0.0001

Data Index: 1624042 (Python Code)

Max Activating Token Index: 491

Text #19

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1396309 (Python Code)

Max Activating Token Index: 69