Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3195 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2751. Min Range: -1.2751

Max Act: 1.2141. Min Act: -0.0000

Data Index: 988797 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 1.2751. Min Range: -1.2751

Max Act: 1.2751. Min Act: -0.0000

Data Index: 51369 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 1.2751. Min Range: -1.2751

Max Act: 1.1607. Min Act: -0.0000

Data Index: 1174750 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9969. Min Act: -0.0000

Data Index: 1049658 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 1.2751. Min Range: -1.2751

Max Act: 1.0498. Min Act: -0.0000

Data Index: 535411 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.2751. Min Range: -1.2751

Max Act: 1.0521. Min Act: -0.0000

Data Index: 494210 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 1.2751. Min Range: -1.2751

Max Act: 1.0594. Min Act: 0.0000

Data Index: 1116907 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9429. Min Act: -0.0000

Data Index: 490984 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9662. Min Act: -0.0000

Data Index: 927153 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9847. Min Act: -0.0000

Data Index: 629222 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1296658 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1250969 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9756. Min Act: -0.0000

Data Index: 616331 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9739. Min Act: -0.0000

Data Index: 573787 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9620. Min Act: -0.0000

Data Index: 571480 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9623. Min Act: -0.0000

Data Index: 620591 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9567. Min Act: -0.0000

Data Index: 407733 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9496. Min Act: -0.0000

Data Index: 756084 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9229. Min Act: -0.0000

Data Index: 38622 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9470. Min Act: -0.0000

Data Index: 320571 (C4 (Web Text))

Max Activating Token Index: 388