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

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

Neuron 2627 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1445508 (Python Code)

Max Activating Token Index: 801

Text #1

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1580283 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1619459 (Python Code)

Max Activating Token Index: 725

Text #3

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1447586 (Python Code)

Max Activating Token Index: 254

Text #4

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1436034 (Python Code)

Max Activating Token Index: 808

Text #5

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7366. Min Act: -0.0000

Data Index: 260894 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1579306 (Python Code)

Max Activating Token Index: 173

Text #7

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1503923 (Python Code)

Max Activating Token Index: 753

Text #8

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1432821 (Python Code)

Max Activating Token Index: 987

Text #9

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1382728 (Python Code)

Max Activating Token Index: 832

Text #10

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1553250 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1506026 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1477564 (Python Code)

Max Activating Token Index: 426

Text #13

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1421512 (Python Code)

Max Activating Token Index: 335

Text #14

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1377874 (Python Code)

Max Activating Token Index: 425

Text #15

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6613. Min Act: -0.0000

Data Index: 284629 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1540836 (Python Code)

Max Activating Token Index: 871

Text #17

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1538612 (Python Code)

Max Activating Token Index: 722

Text #18

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1549583 (Python Code)

Max Activating Token Index: 626

Text #19

Max Range: 0.7977. Min Range: -0.7977

Max Act: 0.6741. Min Act: -0.0000

Data Index: 473607 (C4 (Web Text))

Max Activating Token Index: 403