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

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

Neuron 2521 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9258. Min Range: -2.9258

Max Act: 2.9258. Min Act: -0.0000

Data Index: 1459740 (Python Code)

Max Activating Token Index: 610

Text #1

Max Range: 2.9258. Min Range: -2.9258

Max Act: 2.3943. Min Act: -0.0000

Data Index: 1471990 (Python Code)

Max Activating Token Index: 827

Text #2

Max Range: 2.9258. Min Range: -2.9258

Max Act: 2.4981. Min Act: -0.0000

Data Index: 1474981 (Python Code)

Max Activating Token Index: 527

Text #3

Max Range: 2.9258. Min Range: -2.9258

Max Act: 2.4475. Min Act: -0.0000

Data Index: 1525512 (Python Code)

Max Activating Token Index: 634

Text #4

Max Range: 2.9258. Min Range: -2.9258

Max Act: 2.4096. Min Act: -0.0000

Data Index: 1510122 (Python Code)

Max Activating Token Index: 753

Text #5

Max Range: 2.9258. Min Range: -2.9258

Max Act: 2.3147. Min Act: -0.0000

Data Index: 1425023 (Python Code)

Max Activating Token Index: 234

Text #6

Max Range: 2.9258. Min Range: -2.9258

Max Act: 2.2661. Min Act: -0.0000

Data Index: 1491955 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 2.9258. Min Range: -2.9258

Max Act: 2.3763. Min Act: -0.0000

Data Index: 1480568 (Python Code)

Max Activating Token Index: 508

Text #8

Max Range: 2.9258. Min Range: -2.9258

Max Act: 2.0131. Min Act: -0.0000

Data Index: 1591287 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 2.9258. Min Range: -2.9258

Max Act: 2.1457. Min Act: -0.0000

Data Index: 1413006 (Python Code)

Max Activating Token Index: 636

Text #10

Max Range: 2.9258. Min Range: -2.9258

Max Act: 1.8544. Min Act: -0.0000

Data Index: 1555085 (Python Code)

Max Activating Token Index: 478

Text #11

Max Range: 2.9258. Min Range: -2.9258

Max Act: 1.8519. Min Act: -0.0000

Data Index: 1371124 (Python Code)

Max Activating Token Index: 291

Text #12

Max Range: 2.9258. Min Range: -2.9258

Max Act: 1.7368. Min Act: -0.0000

Data Index: 1655612 (Python Code)

Max Activating Token Index: 517

Text #13

Max Range: 2.9258. Min Range: -2.9258

Max Act: 1.7990. Min Act: -0.0000

Data Index: 1642286 (Python Code)

Max Activating Token Index: 156

Text #14

Max Range: 2.9258. Min Range: -2.9258

Max Act: 1.8020. Min Act: -0.0000

Data Index: 1466264 (Python Code)

Max Activating Token Index: 539

Text #15

Max Range: 2.9258. Min Range: -2.9258

Max Act: 1.7959. Min Act: -0.0000

Data Index: 1499878 (Python Code)

Max Activating Token Index: 681

Text #16

Max Range: 2.9258. Min Range: -2.9258

Max Act: 1.7162. Min Act: -0.0000

Data Index: 1439792 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 2.9258. Min Range: -2.9258

Max Act: 1.6943. Min Act: -0.0000

Data Index: 1410303 (Python Code)

Max Activating Token Index: 967

Text #18

Max Range: 2.9258. Min Range: -2.9258

Max Act: 1.3946. Min Act: -0.0000

Data Index: 1612628 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 2.9258. Min Range: -2.9258

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1374673 (Python Code)

Max Activating Token Index: 817