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

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

Neuron 226 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.3267. Min Act: -0.0000

Data Index: 1547085 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.2250. Min Act: -0.0000

Data Index: 1638781 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0939. Min Act: -0.0000

Data Index: 1481691 (Python Code)

Max Activating Token Index: 1008

Text #3

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1547325 (Python Code)

Max Activating Token Index: 409

Text #4

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1451610 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1626307 (Python Code)

Max Activating Token Index: 562

Text #6

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1545300 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1377377 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8519. Min Act: -0.0000

Data Index: 1635962 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.9647. Min Act: 0.0000

Data Index: 1386212 (Python Code)

Max Activating Token Index: 615

Text #10

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1370162 (Python Code)

Max Activating Token Index: 623

Text #11

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1606744 (Python Code)

Max Activating Token Index: 439

Text #12

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8288. Min Act: 0.0000

Data Index: 1499880 (Python Code)

Max Activating Token Index: 662

Text #13

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1510609 (Python Code)

Max Activating Token Index: 787

Text #14

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8210. Min Act: 0.0000

Data Index: 1506533 (Python Code)

Max Activating Token Index: 761

Text #15

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1362099 (Python Code)

Max Activating Token Index: 705

Text #16

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1527663 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1436075 (Python Code)

Max Activating Token Index: 591

Text #18

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1616493 (Python Code)

Max Activating Token Index: 476

Text #19

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7154. Min Act: 0.0000

Data Index: 1403322 (Python Code)

Max Activating Token Index: 394