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

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

Neuron 991 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.7008. Min Act: -0.0002

Data Index: 635114 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.7136. Min Act: -0.0001

Data Index: 825447 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6384. Min Act: -0.0002

Data Index: 467670 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6589. Min Act: -0.0002

Data Index: 1008969 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6140. Min Act: -0.0002

Data Index: 115539 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6017. Min Act: -0.0002

Data Index: 413915 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6441. Min Act: -0.0002

Data Index: 471298 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5834. Min Act: -0.0002

Data Index: 665600 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6749. Min Act: -0.0001

Data Index: 829080 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6114. Min Act: -0.0002

Data Index: 1238891 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6510. Min Act: -0.0002

Data Index: 689942 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5808. Min Act: -0.0002

Data Index: 122554 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5869. Min Act: -0.0001

Data Index: 494792 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5842. Min Act: -0.0001

Data Index: 999980 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6106. Min Act: -0.0002

Data Index: 240332 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5824. Min Act: -0.0002

Data Index: 562985 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5608. Min Act: -0.0001

Data Index: 323480 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5800. Min Act: -0.0001

Data Index: 995533 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5637. Min Act: -0.0002

Data Index: 1000265 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5395. Min Act: -0.0002

Data Index: 390036 (C4 (Web Text))

Max Activating Token Index: 212