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

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

Neuron 5117 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1107752 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3278. Min Act: -0.0000

Data Index: 304342 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3209. Min Act: -0.0000

Data Index: 967000 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1127620 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3134. Min Act: -0.0000

Data Index: 194809 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3037. Min Act: -0.0000

Data Index: 721081 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3044. Min Act: -0.0000

Data Index: 609899 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3006. Min Act: -0.0000

Data Index: 268910 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2979. Min Act: -0.0000

Data Index: 356148 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2929. Min Act: -0.0000

Data Index: 452672 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2925. Min Act: -0.0000

Data Index: 307368 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1216487 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2904. Min Act: -0.0000

Data Index: 509958 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2824. Min Act: -0.0000

Data Index: 393065 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2618. Min Act: -0.0000

Data Index: 557360 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2639. Min Act: -0.0000

Data Index: 440941 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2743. Min Act: -0.0000

Data Index: 159658 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2850. Min Act: -0.0000

Data Index: 522881 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2565. Min Act: -0.0000

Data Index: 135977 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1073968 (C4 (Web Text))

Max Activating Token Index: 266