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

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

Neuron 2243 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: 2.0439. Min Range: -2.0439

Max Act: 2.0439. Min Act: -0.0000

Data Index: 511466 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.6207. Min Act: -0.0000

Data Index: 357896 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.4917. Min Act: -0.0000

Data Index: 892803 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.4800. Min Act: -0.0000

Data Index: 154352 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.4993. Min Act: -0.0000

Data Index: 614335 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.4395. Min Act: -0.0000

Data Index: 1010535 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.4314. Min Act: -0.0000

Data Index: 210751 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.4863. Min Act: -0.0000

Data Index: 645038 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.4068. Min Act: -0.0000

Data Index: 1262070 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.2874. Min Act: -0.0000

Data Index: 723467 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.2975. Min Act: -0.0000

Data Index: 522514 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.2808. Min Act: -0.0000

Data Index: 575306 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.2652. Min Act: -0.0000

Data Index: 87811 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.3304. Min Act: -0.0000

Data Index: 858733 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.1906. Min Act: -0.0000

Data Index: 375045 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.3552. Min Act: -0.0000

Data Index: 345793 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.2596. Min Act: -0.0000

Data Index: 661277 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.3907. Min Act: -0.0000

Data Index: 525935 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.3835. Min Act: -0.0000

Data Index: 490754 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 2.0439. Min Range: -2.0439

Max Act: 1.3417. Min Act: -0.0000

Data Index: 663726 (C4 (Web Text))

Max Activating Token Index: 708