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

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

Neuron 297 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1506683 (Python Code)

Max Activating Token Index: 563

Text #1

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1574779 (Python Code)

Max Activating Token Index: 891

Text #2

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1580501 (Python Code)

Max Activating Token Index: 1009

Text #3

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1432321 (Python Code)

Max Activating Token Index: 557

Text #4

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3640. Min Act: -0.0000

Data Index: 37372 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1456337 (Python Code)

Max Activating Token Index: 187

Text #6

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1434301 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3455. Min Act: -0.0000

Data Index: 549107 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1634492 (Python Code)

Max Activating Token Index: 824

Text #9

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1388959 (Python Code)

Max Activating Token Index: 301

Text #10

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1539488 (Python Code)

Max Activating Token Index: 137

Text #11

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1510911 (Python Code)

Max Activating Token Index: 406

Text #12

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1641501 (Python Code)

Max Activating Token Index: 547

Text #13

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1387675 (Python Code)

Max Activating Token Index: 456

Text #14

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1029296 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1648640 (Python Code)

Max Activating Token Index: 663

Text #16

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3062. Min Act: -0.0000

Data Index: 437479 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2715. Min Act: -0.0000

Data Index: 797521 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1472394 (Python Code)

Max Activating Token Index: 713

Text #19

Max Range: 0.4184. Min Range: -0.4184

Max Act: 0.3172. Min Act: -0.0000

Data Index: 196160 (C4 (Web Text))

Max Activating Token Index: 295