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

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

Neuron 2492 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.2701. Min Act: -0.0000

Data Index: 40054 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.2701. Min Range: -1.2701

Max Act: 1.0882. Min Act: -0.0000

Data Index: 87533 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9487. Min Act: -0.0000

Data Index: 546522 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1036843 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9169. Min Act: -0.0000

Data Index: 459104 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1001040 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1171355 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9165. Min Act: -0.0000

Data Index: 192393 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9014. Min Act: -0.0000

Data Index: 777057 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1177154 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.8331. Min Act: -0.0000

Data Index: 374544 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9124. Min Act: -0.0000

Data Index: 215580 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.8901. Min Act: -0.0000

Data Index: 87563 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1130866 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.9107. Min Act: -0.0000

Data Index: 372561 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.8684. Min Act: 0.0000

Data Index: 741783 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.8176. Min Act: 0.0000

Data Index: 138437 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.8515. Min Act: -0.0000

Data Index: 330646 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.7952. Min Act: -0.0000

Data Index: 666304 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 1.2701. Min Range: -1.2701

Max Act: 0.8139. Min Act: -0.0000

Data Index: 728135 (C4 (Web Text))

Max Activating Token Index: 190