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

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

Neuron 5318 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9536. Min Range: -3.9536

Max Act: 3.6113. Min Act: -0.0000

Data Index: 672737 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 3.9536. Min Range: -3.9536

Max Act: 3.5135. Min Act: -0.0000

Data Index: 1006986 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 3.9536. Min Range: -3.9536

Max Act: 3.9536. Min Act: -0.0000

Data Index: 881814 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.9391. Min Act: -0.0000

Data Index: 822925 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.7753. Min Act: -0.0000

Data Index: 819666 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 3.9536. Min Range: -3.9536

Max Act: 3.3707. Min Act: -0.0000

Data Index: 274965 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.7911. Min Act: -0.0000

Data Index: 816605 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 3.9536. Min Range: -3.9536

Max Act: 3.0698. Min Act: -0.0000

Data Index: 1309618 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.7176. Min Act: -0.0000

Data Index: 57433 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 3.9536. Min Range: -3.9536

Max Act: 3.0332. Min Act: -0.0000

Data Index: 1077764 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.8470. Min Act: -0.0000

Data Index: 1288315 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.6748. Min Act: -0.0000

Data Index: 380866 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.7300. Min Act: -0.0000

Data Index: 1640887 (Python Code)

Max Activating Token Index: 455

Text #13

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.8548. Min Act: -0.0000

Data Index: 1051275 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.4893. Min Act: -0.0000

Data Index: 1539462 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.2047. Min Act: -0.0000

Data Index: 149120 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.2987. Min Act: -0.0000

Data Index: 1139685 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.3935. Min Act: -0.0000

Data Index: 207022 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.2194. Min Act: -0.0000

Data Index: 1566341 (Python Code)

Max Activating Token Index: 522

Text #19

Max Range: 3.9536. Min Range: -3.9536

Max Act: 2.1277. Min Act: -0.0000

Data Index: 1615854 (Python Code)

Max Activating Token Index: 616