Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 846 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0274. Min Range: -1.0274

Max Act: 1.0274. Min Act: -0.0001

Data Index: 1553655 (Python Code)

Max Activating Token Index: 312

Text #1

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8511. Min Act: -0.0001

Data Index: 1567219 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8326. Min Act: -0.0001

Data Index: 1366735 (Python Code)

Max Activating Token Index: 362

Text #3

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.9491. Min Act: -0.0001

Data Index: 1503500 (Python Code)

Max Activating Token Index: 843

Text #4

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8886. Min Act: -0.0001

Data Index: 1433506 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8508. Min Act: -0.0001

Data Index: 1390188 (Python Code)

Max Activating Token Index: 107

Text #6

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8083. Min Act: -0.0001

Data Index: 1372074 (Python Code)

Max Activating Token Index: 295

Text #7

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8200. Min Act: -0.0001

Data Index: 1592630 (Python Code)

Max Activating Token Index: 1010

Text #8

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7842. Min Act: -0.0001

Data Index: 1531898 (Python Code)

Max Activating Token Index: 254

Text #9

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7892. Min Act: -0.0001

Data Index: 1628728 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8320. Min Act: -0.0001

Data Index: 1445353 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1553592 (Python Code)

Max Activating Token Index: 79

Text #12

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7957. Min Act: -0.0001

Data Index: 1614815 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7623. Min Act: -0.0001

Data Index: 1523934 (Python Code)

Max Activating Token Index: 156

Text #14

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7649. Min Act: -0.0001

Data Index: 1601376 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7548. Min Act: -0.0001

Data Index: 1360156 (Python Code)

Max Activating Token Index: 959

Text #16

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.8067. Min Act: -0.0001

Data Index: 1467518 (Python Code)

Max Activating Token Index: 735

Text #17

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7735. Min Act: -0.0001

Data Index: 1505188 (Python Code)

Max Activating Token Index: 653

Text #18

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7773. Min Act: -0.0001

Data Index: 1468434 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 1.0274. Min Range: -1.0274

Max Act: 0.7459. Min Act: -0.0001

Data Index: 1540612 (Python Code)

Max Activating Token Index: 850