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

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

Neuron 3085 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: 2.4444. Min Range: -2.4444

Max Act: 2.4297. Min Act: -0.0000

Data Index: 1627037 (Python Code)

Max Activating Token Index: 245

Text #1

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.3840. Min Act: -0.0000

Data Index: 1588939 (Python Code)

Max Activating Token Index: 521

Text #2

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.2044. Min Act: -0.0001

Data Index: 1516622 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.4444. Min Act: -0.0000

Data Index: 1523475 (Python Code)

Max Activating Token Index: 874

Text #4

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.1786. Min Act: -0.0001

Data Index: 1360807 (Python Code)

Max Activating Token Index: 834

Text #5

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.3513. Min Act: -0.0000

Data Index: 1505344 (Python Code)

Max Activating Token Index: 895

Text #6

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.1407. Min Act: -0.0000

Data Index: 1378319 (Python Code)

Max Activating Token Index: 850

Text #7

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.7165. Min Act: -0.0000

Data Index: 1499445 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.0429. Min Act: -0.0000

Data Index: 1634842 (Python Code)

Max Activating Token Index: 147

Text #9

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.1135. Min Act: -0.0000

Data Index: 1539314 (Python Code)

Max Activating Token Index: 1005

Text #10

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.0929. Min Act: -0.0000

Data Index: 1432492 (Python Code)

Max Activating Token Index: 806

Text #11

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.9318. Min Act: -0.0000

Data Index: 1438025 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.9343. Min Act: -0.0000

Data Index: 1546171 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.9292. Min Act: -0.0000

Data Index: 1582019 (Python Code)

Max Activating Token Index: 552

Text #14

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.7234. Min Act: -0.0001

Data Index: 1620262 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.9061. Min Act: -0.0000

Data Index: 1549752 (Python Code)

Max Activating Token Index: 239

Text #16

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.6777. Min Act: -0.0000

Data Index: 1614111 (Python Code)

Max Activating Token Index: 368

Text #17

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.8561. Min Act: -0.0000

Data Index: 1643973 (Python Code)

Max Activating Token Index: 607

Text #18

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.7930. Min Act: -0.0001

Data Index: 1441616 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.6189. Min Act: -0.0001

Data Index: 1579660 (Python Code)

Max Activating Token Index: 267