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

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

Neuron 1595 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.8745. Min Act: -0.0000

Data Index: 310064 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 3.1651. Min Range: -3.1651

Max Act: 3.1651. Min Act: -0.0000

Data Index: 1501861 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.9544. Min Act: -0.0000

Data Index: 826045 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.7485. Min Act: -0.0000

Data Index: 531488 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.5588. Min Act: -0.0000

Data Index: 592983 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.4895. Min Act: -0.0000

Data Index: 1258219 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.5233. Min Act: -0.0000

Data Index: 123999 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.3793. Min Act: -0.0000

Data Index: 643488 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.3557. Min Act: -0.0000

Data Index: 684639 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.4442. Min Act: -0.0000

Data Index: 610055 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.3093. Min Act: -0.0000

Data Index: 1400997 (Python Code)

Max Activating Token Index: 422

Text #11

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.4277. Min Act: -0.0000

Data Index: 974398 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.3824. Min Act: -0.0000

Data Index: 1083704 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.3631. Min Act: -0.0000

Data Index: 545373 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.3449. Min Act: -0.0000

Data Index: 232029 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.1910. Min Act: -0.0000

Data Index: 991410 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.3153. Min Act: -0.0000

Data Index: 959598 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.1732. Min Act: -0.0000

Data Index: 1259273 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.1842. Min Act: -0.0000

Data Index: 661645 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 3.1651. Min Range: -3.1651

Max Act: 2.2905. Min Act: -0.0000

Data Index: 858720 (C4 (Web Text))

Max Activating Token Index: 791