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

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

Neuron 3652 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1466419 (Python Code)

Max Activating Token Index: 917

Text #1

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1465197 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1474481 (Python Code)

Max Activating Token Index: 609

Text #3

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1369650 (Python Code)

Max Activating Token Index: 286

Text #4

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1410774 (Python Code)

Max Activating Token Index: 759

Text #5

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1478177 (Python Code)

Max Activating Token Index: 365

Text #6

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1499863 (Python Code)

Max Activating Token Index: 440

Text #7

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1384365 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1480914 (Python Code)

Max Activating Token Index: 630

Text #9

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1594592 (Python Code)

Max Activating Token Index: 921

Text #10

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1430623 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1517160 (Python Code)

Max Activating Token Index: 865

Text #12

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1424864 (Python Code)

Max Activating Token Index: 292

Text #13

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1434400 (Python Code)

Max Activating Token Index: 578

Text #14

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1489147 (Python Code)

Max Activating Token Index: 858

Text #15

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1387311 (Python Code)

Max Activating Token Index: 421

Text #16

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1416980 (Python Code)

Max Activating Token Index: 93

Text #17

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1406471 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1440024 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 0.8979. Min Range: -0.8979

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1476001 (Python Code)

Max Activating Token Index: 1012