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

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

Neuron 1791 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.8083. Min Act: -0.0000

Data Index: 1215589 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.6202. Min Act: -0.0000

Data Index: 369643 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.3317. Min Act: -0.0000

Data Index: 487676 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.7866. Min Act: -0.0000

Data Index: 1123296 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.4946. Min Act: -0.0000

Data Index: 512507 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 4.8083. Min Range: -4.8083

Max Act: 3.9695. Min Act: -0.0000

Data Index: 686389 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.7496. Min Act: -0.0000

Data Index: 447581 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.4669. Min Act: -0.0000

Data Index: 595173 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.2589. Min Act: -0.0000

Data Index: 811860 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.2099. Min Act: -0.0000

Data Index: 1004938 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.0132. Min Act: -0.0000

Data Index: 223978 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 4.8083. Min Range: -4.8083

Max Act: 3.6254. Min Act: -0.0000

Data Index: 105225 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 4.8083. Min Range: -4.8083

Max Act: 4.1308. Min Act: -0.0000

Data Index: 219486 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 4.8083. Min Range: -4.8083

Max Act: 3.9569. Min Act: -0.0000

Data Index: 53115 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 4.8083. Min Range: -4.8083

Max Act: 3.5872. Min Act: -0.0000

Data Index: 432234 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 4.8083. Min Range: -4.8083

Max Act: 3.8931. Min Act: -0.0000

Data Index: 149415 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 4.8083. Min Range: -4.8083

Max Act: 3.8479. Min Act: -0.0000

Data Index: 307451 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 4.8083. Min Range: -4.8083

Max Act: 3.9590. Min Act: -0.0000

Data Index: 222595 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 4.8083. Min Range: -4.8083

Max Act: 3.5810. Min Act: -0.0000

Data Index: 812581 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 4.8083. Min Range: -4.8083

Max Act: 3.5665. Min Act: -0.0000

Data Index: 439246 (C4 (Web Text))

Max Activating Token Index: 568