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

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

Neuron 1990 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1632523 (Python Code)

Max Activating Token Index: 874

Text #1

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1542067 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1370820 (Python Code)

Max Activating Token Index: 251

Text #3

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1402828 (Python Code)

Max Activating Token Index: 419

Text #4

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1596862 (Python Code)

Max Activating Token Index: 243

Text #5

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1459222 (Python Code)

Max Activating Token Index: 470

Text #6

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1575784 (Python Code)

Max Activating Token Index: 568

Text #7

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1487657 (Python Code)

Max Activating Token Index: 643

Text #8

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1431740 (Python Code)

Max Activating Token Index: 612

Text #9

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1524217 (Python Code)

Max Activating Token Index: 780

Text #10

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1449180 (Python Code)

Max Activating Token Index: 216

Text #11

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1480755 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1451145 (Python Code)

Max Activating Token Index: 942

Text #13

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1648549 (Python Code)

Max Activating Token Index: 738

Text #14

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1488783 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1537181 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1459967 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1418990 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1516104 (Python Code)

Max Activating Token Index: 490

Text #19

Max Range: 0.6144. Min Range: -0.6144

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1625127 (Python Code)

Max Activating Token Index: 988