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

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

Neuron 5457 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.3153. Min Act: -0.0000

Data Index: 197398 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.2129. Min Act: -0.0000

Data Index: 394106 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.2023. Min Act: -0.0000

Data Index: 13369 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0739. Min Act: -0.0000

Data Index: 113525 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1979. Min Act: -0.0000

Data Index: 487235 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1855. Min Act: -0.0000

Data Index: 44263 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1016. Min Act: -0.0000

Data Index: 648224 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.1593. Min Act: -0.0000

Data Index: 538386 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0887. Min Act: -0.0000

Data Index: 36940 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0768. Min Act: -0.0000

Data Index: 72071 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0063. Min Act: -0.0000

Data Index: 953015 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0811. Min Act: -0.0000

Data Index: 659899 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0227. Min Act: -0.0000

Data Index: 1283925 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 1.3153. Min Range: -1.3153

Max Act: 1.0460. Min Act: -0.0000

Data Index: 866140 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.9995. Min Act: -0.0000

Data Index: 828677 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.9936. Min Act: -0.0000

Data Index: 492021 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.9580. Min Act: -0.0000

Data Index: 303816 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.9672. Min Act: -0.0000

Data Index: 672488 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.9695. Min Act: -0.0000

Data Index: 353902 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.3153. Min Range: -1.3153

Max Act: 0.9494. Min Act: -0.0000

Data Index: 163281 (C4 (Web Text))

Max Activating Token Index: 940