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

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

Neuron 1629 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1496. Min Range: -2.1496

Max Act: 2.1496. Min Act: -0.0000

Data Index: 480292 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.9696. Min Act: -0.0000

Data Index: 1021704 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.8593. Min Act: -0.0000

Data Index: 845348 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.7943. Min Act: -0.0000

Data Index: 541621 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.6204. Min Act: -0.0000

Data Index: 1288625 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.7077. Min Act: -0.0000

Data Index: 884662 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.6541. Min Act: -0.0000

Data Index: 1144604 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.4959. Min Act: -0.0000

Data Index: 180563 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.6029. Min Act: -0.0000

Data Index: 864728 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.4802. Min Act: -0.0000

Data Index: 950433 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.2655. Min Act: -0.0000

Data Index: 1133396 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.4064. Min Act: -0.0000

Data Index: 408142 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.3946. Min Act: -0.0000

Data Index: 1248046 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.4714. Min Act: -0.0000

Data Index: 1291468 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.3987. Min Act: -0.0000

Data Index: 141907 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.3760. Min Act: -0.0000

Data Index: 1335460 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.3688. Min Act: -0.0000

Data Index: 52429 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.3304. Min Act: -0.0000

Data Index: 666603 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.2560. Min Act: -0.0000

Data Index: 832875 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 2.1496. Min Range: -2.1496

Max Act: 1.2527. Min Act: -0.0000

Data Index: 734154 (C4 (Web Text))

Max Activating Token Index: 1015