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

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

Neuron 5824 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: 1.2706. Min Range: -1.2706

Max Act: 1.2706. Min Act: -0.0000

Data Index: 256986 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.1019. Min Act: -0.0000

Data Index: 416499 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0813. Min Act: -0.0000

Data Index: 287869 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0468. Min Act: -0.0000

Data Index: 484712 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0511. Min Act: -0.0000

Data Index: 491710 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1356276 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0435. Min Act: -0.0000

Data Index: 176574 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0186. Min Act: -0.0000

Data Index: 525939 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0134. Min Act: -0.0000

Data Index: 463498 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0106. Min Act: -0.0000

Data Index: 444416 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0052. Min Act: -0.0000

Data Index: 787895 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.2706. Min Range: -1.2706

Max Act: 0.9937. Min Act: -0.0000

Data Index: 474770 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 1.2706. Min Range: -1.2706

Max Act: 0.9107. Min Act: -0.0000

Data Index: 837428 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 1.2706. Min Range: -1.2706

Max Act: 0.9212. Min Act: -0.0000

Data Index: 550306 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.2706. Min Range: -1.2706

Max Act: 0.9615. Min Act: -0.0000

Data Index: 150816 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 1.2706. Min Range: -1.2706

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1003199 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 1.2706. Min Range: -1.2706

Max Act: 0.9464. Min Act: -0.0000

Data Index: 674319 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.2706. Min Range: -1.2706

Max Act: 0.8852. Min Act: -0.0000

Data Index: 889802 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.2706. Min Range: -1.2706

Max Act: 0.9403. Min Act: -0.0000

Data Index: 287266 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.2706. Min Range: -1.2706

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1198512 (C4 (Web Text))

Max Activating Token Index: 106