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

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

Neuron 3017 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.3495. Min Act: -0.0001

Data Index: 247043 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.3923. Min Act: -0.0001

Data Index: 197264 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.3375. Min Act: -0.0001

Data Index: 352540 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2984. Min Act: -0.0001

Data Index: 1353317 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.3468. Min Act: -0.0001

Data Index: 825414 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2837. Min Act: -0.0001

Data Index: 952268 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2950. Min Act: -0.0001

Data Index: 604320 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.3262. Min Act: -0.0001

Data Index: 925062 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2925. Min Act: -0.0001

Data Index: 1306626 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2784. Min Act: -0.0001

Data Index: 716773 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2743. Min Act: -0.0001

Data Index: 961981 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2737. Min Act: -0.0001

Data Index: 900416 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2948. Min Act: -0.0001

Data Index: 1036431 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2592. Min Act: -0.0001

Data Index: 799952 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2865. Min Act: -0.0001

Data Index: 80118 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2759. Min Act: -0.0001

Data Index: 1354402 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2215. Min Act: -0.0001

Data Index: 197167 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2889. Min Act: -0.0001

Data Index: 684833 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2697. Min Act: -0.0001

Data Index: 869174 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.3923. Min Range: -0.3923

Max Act: 0.2629. Min Act: -0.0001

Data Index: 171087 (C4 (Web Text))

Max Activating Token Index: 288