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

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

Neuron 4159 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.5037. Min Act: -0.0001

Data Index: 23810 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3593. Min Act: -0.0001

Data Index: 1304599 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3473. Min Act: -0.0001

Data Index: 1073438 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3504. Min Act: -0.0001

Data Index: 25224 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3326. Min Act: -0.0001

Data Index: 365858 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3198. Min Act: -0.0001

Data Index: 1059262 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3297. Min Act: -0.0001

Data Index: 963803 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2958. Min Act: -0.0001

Data Index: 108088 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2809. Min Act: -0.0001

Data Index: 570053 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2789. Min Act: -0.0001

Data Index: 738305 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2677. Min Act: -0.0001

Data Index: 392646 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2860. Min Act: -0.0001

Data Index: 379363 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2844. Min Act: -0.0001

Data Index: 397918 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2918. Min Act: -0.0001

Data Index: 494219 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2810. Min Act: -0.0001

Data Index: 61384 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2761. Min Act: -0.0001

Data Index: 1136507 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1158901 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2697. Min Act: -0.0001

Data Index: 1310006 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2600. Min Act: -0.0001

Data Index: 689564 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2827. Min Act: -0.0001

Data Index: 690731 (C4 (Web Text))

Max Activating Token Index: 280