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

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

Neuron 1673 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.7858. Min Act: -0.0000

Data Index: 1636275 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.3315. Min Act: -0.0000

Data Index: 1522686 (Python Code)

Max Activating Token Index: 930

Text #2

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.2698. Min Act: -0.0000

Data Index: 1477425 (Python Code)

Max Activating Token Index: 975

Text #3

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.1428. Min Act: -0.0000

Data Index: 1645483 (Python Code)

Max Activating Token Index: 221

Text #4

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.9291. Min Act: -0.0000

Data Index: 1532874 (Python Code)

Max Activating Token Index: 898

Text #5

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.0408. Min Act: -0.0000

Data Index: 1545436 (Python Code)

Max Activating Token Index: 213

Text #6

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.8964. Min Act: -0.0000

Data Index: 1465338 (Python Code)

Max Activating Token Index: 672

Text #7

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.9496. Min Act: -0.0000

Data Index: 1596837 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 2.7858. Min Range: -2.7858

Max Act: 2.0328. Min Act: -0.0000

Data Index: 1523420 (Python Code)

Max Activating Token Index: 724

Text #9

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.6280. Min Act: -0.0000

Data Index: 1370178 (Python Code)

Max Activating Token Index: 897

Text #10

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1364607 (Python Code)

Max Activating Token Index: 745

Text #11

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.7607. Min Act: -0.0000

Data Index: 1453079 (Python Code)

Max Activating Token Index: 79

Text #12

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.8231. Min Act: -0.0000

Data Index: 1584567 (Python Code)

Max Activating Token Index: 432

Text #13

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.7360. Min Act: -0.0000

Data Index: 1635876 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.6486. Min Act: -0.0000

Data Index: 1380157 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.7433. Min Act: -0.0000

Data Index: 19349 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.7339. Min Act: -0.0000

Data Index: 1437678 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.7223. Min Act: -0.0000

Data Index: 1394901 (Python Code)

Max Activating Token Index: 506

Text #18

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.6979. Min Act: -0.0000

Data Index: 1614480 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 2.7858. Min Range: -2.7858

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1554709 (Python Code)

Max Activating Token Index: 125