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

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

Neuron 2670 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: 1.0544. Min Range: -1.0544

Max Act: 1.0544. Min Act: -0.0001

Data Index: 60927 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.9733. Min Act: -0.0001

Data Index: 500477 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.9608. Min Act: -0.0001

Data Index: 718078 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.9507. Min Act: -0.0001

Data Index: 1090418 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.9318. Min Act: -0.0001

Data Index: 220489 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.9257. Min Act: -0.0001

Data Index: 333299 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8953. Min Act: -0.0001

Data Index: 322499 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.9149. Min Act: -0.0001

Data Index: 330651 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.9275. Min Act: -0.0001

Data Index: 956155 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.9188. Min Act: -0.0001

Data Index: 897980 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.9024. Min Act: -0.0001

Data Index: 162990 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8931. Min Act: -0.0001

Data Index: 1190399 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8803. Min Act: -0.0001

Data Index: 587734 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8831. Min Act: -0.0001

Data Index: 95017 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8464. Min Act: -0.0001

Data Index: 39249 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8502. Min Act: -0.0001

Data Index: 255642 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8726. Min Act: -0.0001

Data Index: 55293 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8411. Min Act: -0.0001

Data Index: 733635 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8741. Min Act: -0.0001

Data Index: 703526 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 1.0544. Min Range: -1.0544

Max Act: 0.8701. Min Act: -0.0001

Data Index: 617071 (C4 (Web Text))

Max Activating Token Index: 105