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

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

Neuron 2520 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: 1.8879. Min Range: -1.8879

Max Act: 1.8879. Min Act: -0.0000

Data Index: 1438405 (Python Code)

Max Activating Token Index: 976

Text #1

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.7103. Min Act: -0.0000

Data Index: 929253 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.6568. Min Act: -0.0000

Data Index: 963370 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.5615. Min Act: -0.0000

Data Index: 949170 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.7341. Min Act: -0.0000

Data Index: 481357 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.5345. Min Act: -0.0000

Data Index: 1602446 (Python Code)

Max Activating Token Index: 419

Text #6

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.5542. Min Act: -0.0000

Data Index: 847032 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.4747. Min Act: -0.0000

Data Index: 1203986 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.4412. Min Act: -0.0000

Data Index: 235518 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.4681. Min Act: -0.0000

Data Index: 552719 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.4547. Min Act: -0.0000

Data Index: 662119 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3778. Min Act: -0.0000

Data Index: 974444 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3403. Min Act: -0.0000

Data Index: 515940 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3328. Min Act: -0.0000

Data Index: 600297 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1536711 (Python Code)

Max Activating Token Index: 898

Text #15

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3737. Min Act: -0.0000

Data Index: 917380 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3759. Min Act: -0.0000

Data Index: 937907 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3587. Min Act: -0.0000

Data Index: 11985 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.1854. Min Act: -0.0000

Data Index: 36252 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3148. Min Act: -0.0000

Data Index: 558038 (C4 (Web Text))

Max Activating Token Index: 359