Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 147 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7168. Min Range: -3.7168

Max Act: 3.6354. Min Act: -0.0000

Data Index: 763684 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 3.7168. Min Range: -3.7168

Max Act: 3.7168. Min Act: -0.0000

Data Index: 705250 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 3.7168. Min Range: -3.7168

Max Act: 3.3467. Min Act: -0.0000

Data Index: 1134480 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 3.7168. Min Range: -3.7168

Max Act: 3.6506. Min Act: -0.0000

Data Index: 1013691 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 3.7168. Min Range: -3.7168

Max Act: 3.2634. Min Act: -0.0000

Data Index: 1172792 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 3.7168. Min Range: -3.7168

Max Act: 3.1711. Min Act: -0.0000

Data Index: 69970 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 3.7168. Min Range: -3.7168

Max Act: 3.5663. Min Act: -0.0001

Data Index: 974919 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 3.7168. Min Range: -3.7168

Max Act: 3.2197. Min Act: -0.0000

Data Index: 107257 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 3.7168. Min Range: -3.7168

Max Act: 2.7318. Min Act: -0.0000

Data Index: 1186148 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 3.7168. Min Range: -3.7168

Max Act: 2.7605. Min Act: -0.0000

Data Index: 986169 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 3.7168. Min Range: -3.7168

Max Act: 2.9127. Min Act: -0.0000

Data Index: 85479 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 3.7168. Min Range: -3.7168

Max Act: 3.1028. Min Act: -0.0000

Data Index: 614930 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 3.7168. Min Range: -3.7168

Max Act: 2.8576. Min Act: -0.0000

Data Index: 351618 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 3.7168. Min Range: -3.7168

Max Act: 2.7214. Min Act: -0.0000

Data Index: 1218459 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 3.7168. Min Range: -3.7168

Max Act: 2.7015. Min Act: -0.0000

Data Index: 956077 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 3.7168. Min Range: -3.7168

Max Act: 3.0194. Min Act: -0.0000

Data Index: 898611 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 3.7168. Min Range: -3.7168

Max Act: 2.6118. Min Act: -0.0001

Data Index: 467546 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 3.7168. Min Range: -3.7168

Max Act: 2.5568. Min Act: -0.0000

Data Index: 1044599 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 3.7168. Min Range: -3.7168

Max Act: 2.6493. Min Act: -0.0000

Data Index: 318519 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 3.7168. Min Range: -3.7168

Max Act: 2.7734. Min Act: -0.0000

Data Index: 555695 (C4 (Web Text))

Max Activating Token Index: 299