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

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

Neuron 36 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: 3.4217. Min Range: -3.4217

Max Act: 3.4217. Min Act: -0.0000

Data Index: 94282 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.4217. Min Range: -3.4217

Max Act: 3.0563. Min Act: -0.0000

Data Index: 514046 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.9513. Min Act: -0.0000

Data Index: 599524 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 3.4217. Min Range: -3.4217

Max Act: 3.0491. Min Act: -0.0000

Data Index: 1336211 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.8919. Min Act: -0.0000

Data Index: 447772 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.8861. Min Act: -0.0000

Data Index: 682222 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.8739. Min Act: -0.0000

Data Index: 396052 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.7884. Min Act: -0.0000

Data Index: 1353663 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.7395. Min Act: -0.0000

Data Index: 475606 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.6335. Min Act: 0.0000

Data Index: 826552 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.5797. Min Act: -0.0000

Data Index: 1237505 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.6273. Min Act: -0.0000

Data Index: 294075 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.7458. Min Act: -0.0000

Data Index: 872890 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.3496. Min Act: -0.0000

Data Index: 1110588 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.1110. Min Act: -0.0000

Data Index: 530917 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.1587. Min Act: -0.0000

Data Index: 3235 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 3.4217. Min Range: -3.4217

Max Act: 1.9991. Min Act: -0.0000

Data Index: 1198073 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.0827. Min Act: -0.0000

Data Index: 910990 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.1827. Min Act: -0.0000

Data Index: 657382 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 3.4217. Min Range: -3.4217

Max Act: 2.0312. Min Act: -0.0000

Data Index: 276640 (C4 (Web Text))

Max Activating Token Index: 147