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

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

Neuron 55 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: 2.5915. Min Range: -2.5915

Max Act: 2.5915. Min Act: -0.0000

Data Index: 425244 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.4343. Min Act: -0.0000

Data Index: 478632 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.2322. Min Act: -0.0000

Data Index: 666964 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.3403. Min Act: -0.0000

Data Index: 599003 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.2986. Min Act: -0.0000

Data Index: 1149904 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.2868. Min Act: -0.0000

Data Index: 939904 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.3966. Min Act: -0.0000

Data Index: 988982 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.2503. Min Act: -0.0000

Data Index: 555306 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.2386. Min Act: -0.0000

Data Index: 365037 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.1140. Min Act: -0.0000

Data Index: 626781 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.2134. Min Act: -0.0000

Data Index: 1324129 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.0760. Min Act: -0.0000

Data Index: 577869 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.1889. Min Act: -0.0000

Data Index: 1317089 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.1572. Min Act: -0.0000

Data Index: 1034889 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.1168. Min Act: -0.0000

Data Index: 963339 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.2603. Min Act: -0.0000

Data Index: 156974 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.1103. Min Act: -0.0000

Data Index: 250668 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.1154. Min Act: -0.0000

Data Index: 413318 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.1023. Min Act: -0.0000

Data Index: 921002 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 2.5915. Min Range: -2.5915

Max Act: 2.0946. Min Act: -0.0000

Data Index: 223900 (C4 (Web Text))

Max Activating Token Index: 616