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

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

Neuron 2350 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.3793. Min Act: -0.0001

Data Index: 376700 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.6751. Min Act: -0.0000

Data Index: 707700 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.4437. Min Act: -0.0000

Data Index: 445667 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.5426. Min Act: -0.0000

Data Index: 1336653 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.2891. Min Act: -0.0000

Data Index: 874861 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.2715. Min Act: -0.0001

Data Index: 1190621 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.2978. Min Act: -0.0000

Data Index: 1028837 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.4982. Min Act: -0.0000

Data Index: 94117 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.2319. Min Act: -0.0000

Data Index: 188905 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.3383. Min Act: -0.0000

Data Index: 714406 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.3261. Min Act: -0.0000

Data Index: 255375 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.3284. Min Act: -0.0000

Data Index: 486366 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.1848. Min Act: -0.0000

Data Index: 404536 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.1794. Min Act: -0.0000

Data Index: 405523 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.3037. Min Act: -0.0000

Data Index: 930771 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.2472. Min Act: -0.0001

Data Index: 943617 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.3637. Min Act: -0.0001

Data Index: 60559 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.4015. Min Act: -0.0000

Data Index: 537624 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.2032. Min Act: -0.0000

Data Index: 69240 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 2.6751. Min Range: -2.6751

Max Act: 2.2232. Min Act: -0.0001

Data Index: 502324 (C4 (Web Text))

Max Activating Token Index: 155