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

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

Neuron 1625 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.4251. Min Act: -0.0001

Data Index: 516326 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3881. Min Act: -0.0001

Data Index: 821089 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3959. Min Act: -0.0001

Data Index: 1253309 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.4015. Min Act: -0.0001

Data Index: 918345 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3611. Min Act: -0.0001

Data Index: 235558 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3795. Min Act: -0.0001

Data Index: 1332098 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3690. Min Act: -0.0001

Data Index: 982311 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3780. Min Act: -0.0000

Data Index: 367064 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3923. Min Act: -0.0001

Data Index: 1319667 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3697. Min Act: -0.0001

Data Index: 836841 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3436. Min Act: -0.0001

Data Index: 869320 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3572. Min Act: -0.0001

Data Index: 423301 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3256. Min Act: -0.0001

Data Index: 396926 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3541. Min Act: -0.0001

Data Index: 1275323 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3245. Min Act: -0.0001

Data Index: 1119202 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3410. Min Act: -0.0001

Data Index: 143052 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3574. Min Act: -0.0001

Data Index: 822883 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3450. Min Act: -0.0001

Data Index: 1021871 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3667. Min Act: -0.0001

Data Index: 744010 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.4251. Min Range: -0.4251

Max Act: 0.3427. Min Act: -0.0000

Data Index: 126628 (C4 (Web Text))

Max Activating Token Index: 435