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

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

Neuron 384 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.3267. Min Act: -0.0001

Data Index: 797987 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0356. Min Act: -0.0001

Data Index: 1091724 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.2065. Min Act: -0.0001

Data Index: 531481 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1144569 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.9855. Min Act: -0.0001

Data Index: 1308229 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0009. Min Act: -0.0000

Data Index: 810280 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0466. Min Act: -0.0000

Data Index: 2227 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8262. Min Act: -0.0001

Data Index: 320730 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7984. Min Act: -0.0001

Data Index: 342222 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1201770 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8846. Min Act: -0.0001

Data Index: 870355 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7097. Min Act: -0.0000

Data Index: 137983 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8027. Min Act: -0.0000

Data Index: 59953 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7948. Min Act: -0.0001

Data Index: 1298392 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7860. Min Act: -0.0001

Data Index: 744238 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.8056. Min Act: -0.0000

Data Index: 769694 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7342. Min Act: -0.0001

Data Index: 1069219 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7738. Min Act: -0.0001

Data Index: 138841 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7868. Min Act: -0.0001

Data Index: 449486 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 1.3267. Min Range: -1.3267

Max Act: 0.7404. Min Act: -0.0001

Data Index: 1165908 (C4 (Web Text))

Max Activating Token Index: 888