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

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

Neuron 521 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.4568. Min Act: -0.0000

Data Index: 205667 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1089676 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1302284 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.4239. Min Act: -0.0000

Data Index: 180226 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.4266. Min Act: -0.0000

Data Index: 137825 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.4119. Min Act: -0.0000

Data Index: 218254 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.4230. Min Act: -0.0000

Data Index: 566592 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1267306 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3989. Min Act: -0.0000

Data Index: 936455 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.4205. Min Act: -0.0000

Data Index: 9680 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.4015. Min Act: -0.0000

Data Index: 354123 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3477. Min Act: -0.0000

Data Index: 766945 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3855. Min Act: -0.0000

Data Index: 959487 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3573. Min Act: -0.0000

Data Index: 756575 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3713. Min Act: -0.0000

Data Index: 525425 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3617. Min Act: -0.0000

Data Index: 49584 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1045637 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3794. Min Act: -0.0000

Data Index: 184661 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3423. Min Act: -0.0000

Data Index: 426069 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.4568. Min Range: -0.4568

Max Act: 0.3530. Min Act: -0.0000

Data Index: 97379 (C4 (Web Text))

Max Activating Token Index: 572