Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2516 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1054. Min Range: -1.1054

Max Act: 1.0654. Min Act: -0.0001

Data Index: 1216728 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9924. Min Act: -0.0001

Data Index: 900547 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9647. Min Act: -0.0001

Data Index: 596395 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 1.1054. Min Range: -1.1054

Max Act: 1.0230. Min Act: -0.0001

Data Index: 1039057 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 1.1054. Min Range: -1.1054

Max Act: 1.0367. Min Act: -0.0001

Data Index: 215991 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9674. Min Act: -0.0001

Data Index: 540894 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8797. Min Act: -0.0001

Data Index: 182602 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9975. Min Act: -0.0001

Data Index: 764790 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9602. Min Act: -0.0001

Data Index: 650440 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.7322. Min Act: -0.0001

Data Index: 1226735 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 1.1054. Min Range: -1.1054

Max Act: 1.1054. Min Act: -0.0001

Data Index: 391431 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8628. Min Act: -0.0001

Data Index: 69047 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8915. Min Act: -0.0001

Data Index: 146640 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9674. Min Act: -0.0001

Data Index: 1355144 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9549. Min Act: -0.0001

Data Index: 1099246 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8661. Min Act: -0.0001

Data Index: 132884 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.6789. Min Act: -0.0001

Data Index: 806871 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8053. Min Act: -0.0001

Data Index: 1296996 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9398. Min Act: -0.0001

Data Index: 74139 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8263. Min Act: -0.0001

Data Index: 405076 (C4 (Web Text))

Max Activating Token Index: 513