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

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

Neuron 4805 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3205. Min Range: -5.3205

Max Act: 5.2008. Min Act: -0.0000

Data Index: 1576510 (Python Code)

Max Activating Token Index: 830

Text #1

Max Range: 5.3205. Min Range: -5.3205

Max Act: 5.3205. Min Act: -0.0000

Data Index: 1619141 (Python Code)

Max Activating Token Index: 495

Text #2

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.8955. Min Act: -0.0000

Data Index: 1644227 (Python Code)

Max Activating Token Index: 146

Text #3

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.7679. Min Act: -0.0000

Data Index: 1531032 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.5235. Min Act: -0.0000

Data Index: 1420147 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.6925. Min Act: -0.0000

Data Index: 1639170 (Python Code)

Max Activating Token Index: 905

Text #6

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.5748. Min Act: -0.0000

Data Index: 1589391 (Python Code)

Max Activating Token Index: 377

Text #7

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.8416. Min Act: -0.0000

Data Index: 1656095 (Python Code)

Max Activating Token Index: 182

Text #8

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.5851. Min Act: -0.0000

Data Index: 1569916 (Python Code)

Max Activating Token Index: 116

Text #9

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.4783. Min Act: -0.0000

Data Index: 1523517 (Python Code)

Max Activating Token Index: 347

Text #10

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.3838. Min Act: -0.0000

Data Index: 1529511 (Python Code)

Max Activating Token Index: 512

Text #11

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.7258. Min Act: -0.0000

Data Index: 1560525 (Python Code)

Max Activating Token Index: 857

Text #12

Max Range: 5.3205. Min Range: -5.3205

Max Act: 3.9962. Min Act: -0.0000

Data Index: 1422823 (Python Code)

Max Activating Token Index: 329

Text #13

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.1598. Min Act: -0.0000

Data Index: 1366522 (Python Code)

Max Activating Token Index: 193

Text #14

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.4421. Min Act: -0.0000

Data Index: 1583681 (Python Code)

Max Activating Token Index: 293

Text #15

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.1182. Min Act: -0.0000

Data Index: 1571956 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.2755. Min Act: -0.0000

Data Index: 1383449 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.0851. Min Act: -0.0000

Data Index: 1479985 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.4418. Min Act: -0.0001

Data Index: 1363002 (Python Code)

Max Activating Token Index: 56

Text #19

Max Range: 5.3205. Min Range: -5.3205

Max Act: 4.2280. Min Act: -0.0000

Data Index: 1567213 (Python Code)

Max Activating Token Index: 59