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

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

Neuron 2796 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3931. Min Act: -0.0002

Data Index: 850536 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3513. Min Act: -0.0002

Data Index: 674235 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3441. Min Act: -0.0002

Data Index: 750958 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3424. Min Act: -0.0002

Data Index: 1342710 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3351. Min Act: -0.0002

Data Index: 1349998 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3340. Min Act: -0.0002

Data Index: 962186 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3196. Min Act: -0.0002

Data Index: 377056 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3086. Min Act: -0.0002

Data Index: 713290 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3083. Min Act: -0.0002

Data Index: 394688 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2950. Min Act: -0.0002

Data Index: 425066 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3036. Min Act: -0.0002

Data Index: 682036 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3115. Min Act: -0.0002

Data Index: 640666 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2979. Min Act: -0.0002

Data Index: 1328054 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2962. Min Act: -0.0002

Data Index: 291700 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2934. Min Act: -0.0002

Data Index: 430184 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2925. Min Act: -0.0002

Data Index: 574195 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2938. Min Act: -0.0002

Data Index: 310439 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2909. Min Act: -0.0002

Data Index: 924858 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2889. Min Act: -0.0002

Data Index: 205918 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2801. Min Act: -0.0002

Data Index: 750058 (C4 (Web Text))

Max Activating Token Index: 696