Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2504 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.4283. Min Range: -2.4283

Max Act: 2.4283. Min Act: -0.0001

Data Index: 652257 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 2.4283. Min Range: -2.4283

Max Act: 2.3057. Min Act: -0.0001

Data Index: 289121 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 2.4283. Min Range: -2.4283

Max Act: 2.1626. Min Act: -0.0000

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 2.4283. Min Range: -2.4283

Max Act: 2.0284. Min Act: -0.0000

Data Index: 1125123 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 2.4283. Min Range: -2.4283

Max Act: 2.0531. Min Act: -0.0001

Data Index: 1336741 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 2.4283. Min Range: -2.4283

Max Act: 2.0648. Min Act: -0.0000

Data Index: 1257202 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9007. Min Act: -0.0000

Data Index: 1566202 (Python Code)

Max Activating Token Index: 534

Text #7

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9955. Min Act: -0.0000

Data Index: 1637648 (Python Code)

Max Activating Token Index: 304

Text #8

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9769. Min Act: -0.0000

Data Index: 1461919 (Python Code)

Max Activating Token Index: 416

Text #9

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.8537. Min Act: -0.0000

Data Index: 273620 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9226. Min Act: -0.0001

Data Index: 1537662 (Python Code)

Max Activating Token Index: 498

Text #11

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9543. Min Act: -0.0001

Data Index: 841687 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9682. Min Act: -0.0000

Data Index: 1571886 (Python Code)

Max Activating Token Index: 548

Text #13

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.8507. Min Act: -0.0000

Data Index: 1434634 (Python Code)

Max Activating Token Index: 568

Text #14

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9924. Min Act: -0.0000

Data Index: 1598672 (Python Code)

Max Activating Token Index: 373

Text #15

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.8971. Min Act: -0.0001

Data Index: 655711 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9964. Min Act: -0.0000

Data Index: 775725 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.8461. Min Act: -0.0001

Data Index: 385624 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.9465. Min Act: -0.0001

Data Index: 1078615 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 2.4283. Min Range: -2.4283

Max Act: 1.7984. Min Act: -0.0001

Data Index: 790642 (C4 (Web Text))

Max Activating Token Index: 317