Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4170 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.6617. Min Act: -0.0000

Data Index: 385565 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1290779 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.5061. Min Act: -0.0000

Data Index: 736893 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4902. Min Act: -0.0000

Data Index: 573935 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1122596 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4812. Min Act: -0.0000

Data Index: 952704 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4636. Min Act: -0.0000

Data Index: 230805 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4972. Min Act: -0.0000

Data Index: 455941 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1335766 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1121369 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4649. Min Act: -0.0000

Data Index: 205131 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1250617 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4542. Min Act: -0.0000

Data Index: 665 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4419. Min Act: -0.0000

Data Index: 842925 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4737. Min Act: -0.0000

Data Index: 967657 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4237. Min Act: -0.0000

Data Index: 499364 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1354684 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4085. Min Act: -0.0000

Data Index: 624173 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.4044. Min Act: -0.0000

Data Index: 370193 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.6617. Min Range: -0.6617

Max Act: 0.3953. Min Act: -0.0000

Data Index: 606595 (C4 (Web Text))

Max Activating Token Index: 1010