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

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

Neuron 3095 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4076. Min Range: -4.4076

Max Act: 4.4076. Min Act: -0.0000

Data Index: 447146 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 4.4076. Min Range: -4.4076

Max Act: 4.3502. Min Act: -0.0000

Data Index: 423646 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.6555. Min Act: -0.0000

Data Index: 1041753 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.6014. Min Act: -0.0000

Data Index: 722789 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.8714. Min Act: -0.0000

Data Index: 1063598 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.6936. Min Act: -0.0000

Data Index: 363328 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.7033. Min Act: -0.0000

Data Index: 830739 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.1664. Min Act: -0.0000

Data Index: 1105317 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.7513. Min Act: -0.0000

Data Index: 34653 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.5972. Min Act: -0.0000

Data Index: 961573 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.5818. Min Act: -0.0000

Data Index: 474224 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.7136. Min Act: -0.0000

Data Index: 1019220 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.3757. Min Act: -0.0000

Data Index: 1267940 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.2943. Min Act: -0.0000

Data Index: 1049775 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.2928. Min Act: -0.0000

Data Index: 674134 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.1978. Min Act: -0.0000

Data Index: 216693 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.3460. Min Act: -0.0000

Data Index: 149826 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.3098. Min Act: -0.0000

Data Index: 110559 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.4726. Min Act: -0.0000

Data Index: 36245 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 4.4076. Min Range: -4.4076

Max Act: 3.3815. Min Act: -0.0000

Data Index: 904282 (C4 (Web Text))

Max Activating Token Index: 115