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

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

Neuron 6061 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1625774 (Python Code)

Max Activating Token Index: 1012

Text #1

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1596339 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0426. Min Act: -0.0000

Data Index: 742283 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1435402 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1450303 (Python Code)

Max Activating Token Index: 136

Text #5

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1440258 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8228. Min Act: -0.0000

Data Index: 976338 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1405973 (Python Code)

Max Activating Token Index: 514

Text #8

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1150503 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1638712 (Python Code)

Max Activating Token Index: 108

Text #10

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1631947 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1464058 (Python Code)

Max Activating Token Index: 570

Text #12

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1577447 (Python Code)

Max Activating Token Index: 705

Text #13

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1634989 (Python Code)

Max Activating Token Index: 914

Text #14

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1643494 (Python Code)

Max Activating Token Index: 438

Text #15

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1582378 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1438569 (Python Code)

Max Activating Token Index: 482

Text #17

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1619483 (Python Code)

Max Activating Token Index: 414

Text #18

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1505592 (Python Code)

Max Activating Token Index: 126

Text #19

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1374406 (Python Code)

Max Activating Token Index: 20