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

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

Neuron 642 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1617. Min Act: -0.0000

Data Index: 193398 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1062. Min Act: -0.0000

Data Index: 742503 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1110. Min Act: -0.0001

Data Index: 177232 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1275216 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.1113. Min Act: -0.0000

Data Index: 820708 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1280474 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0744. Min Act: -0.0000

Data Index: 740391 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0728. Min Act: -0.0001

Data Index: 796013 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0650. Min Act: -0.0001

Data Index: 324645 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0499. Min Act: -0.0001

Data Index: 748194 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0497. Min Act: -0.0001

Data Index: 324248 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0490. Min Act: -0.0001

Data Index: 18072 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0475. Min Act: -0.0000

Data Index: 1255523 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0491. Min Act: -0.0001

Data Index: 457369 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0470. Min Act: -0.0000

Data Index: 899289 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0463. Min Act: -0.0001

Data Index: 514680 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0469. Min Act: -0.0001

Data Index: 138108 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1139238 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1494386 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 0.1617. Min Range: -0.1617

Max Act: 0.0538. Min Act: -0.0001

Data Index: 804567 (C4 (Web Text))

Max Activating Token Index: 383