Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 463 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5679. Min Act: -0.0001

Data Index: 1333033 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3860. Min Act: -0.0001

Data Index: 500789 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3797. Min Act: -0.0001

Data Index: 915827 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3906. Min Act: -0.0001

Data Index: 792297 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3789. Min Act: -0.0001

Data Index: 1105762 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3722. Min Act: -0.0001

Data Index: 92816 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3769. Min Act: -0.0001

Data Index: 852934 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3750. Min Act: -0.0001

Data Index: 1220140 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3431. Min Act: -0.0001

Data Index: 754704 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3372. Min Act: -0.0001

Data Index: 1242668 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3230. Min Act: -0.0001

Data Index: 294152 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3448. Min Act: -0.0001

Data Index: 902459 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3322. Min Act: -0.0001

Data Index: 835498 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3198. Min Act: -0.0001

Data Index: 1318520 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3051. Min Act: -0.0001

Data Index: 290089 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3233. Min Act: -0.0001

Data Index: 31820 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3197. Min Act: -0.0001

Data Index: 353828 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.3076. Min Act: -0.0001

Data Index: 675696 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.2870. Min Act: -0.0001

Data Index: 536704 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.2927. Min Act: -0.0001

Data Index: 114865 (C4 (Web Text))

Max Activating Token Index: 1005