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

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

Neuron 2603 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1138114 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.6218. Min Act: -0.0000

Data Index: 801057 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5505. Min Act: 0.0000

Data Index: 547095 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1144934 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1598507 (Python Code)

Max Activating Token Index: 413

Text #5

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4292. Min Act: -0.0000

Data Index: 519732 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4872. Min Act: -0.0000

Data Index: 245710 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1595330 (Python Code)

Max Activating Token Index: 959

Text #8

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1212082 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4715. Min Act: -0.0000

Data Index: 27503 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4488. Min Act: -0.0000

Data Index: 761913 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1569830 (Python Code)

Max Activating Token Index: 463

Text #12

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4252. Min Act: -0.0000

Data Index: 728445 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1180803 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4216. Min Act: -0.0000

Data Index: 319949 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3931. Min Act: -0.0000

Data Index: 438907 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1477142 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4001. Min Act: -0.0000

Data Index: 85328 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.3921. Min Act: -0.0000

Data Index: 740936 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.6218. Min Range: -0.6218

Max Act: 0.4078. Min Act: -0.0000

Data Index: 590389 (C4 (Web Text))

Max Activating Token Index: 394