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

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

Neuron 1691 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0572. Min Range: -1.0572

Max Act: 1.0572. Min Act: -0.0000

Data Index: 432908 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 1.0572. Min Range: -1.0572

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1032867 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9864. Min Act: -0.0000

Data Index: 636550 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9809. Min Act: -0.0000

Data Index: 432303 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8400. Min Act: -0.0000

Data Index: 89636 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7791. Min Act: -0.0000

Data Index: 303792 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7731. Min Act: -0.0000

Data Index: 386302 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1327208 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8588. Min Act: -0.0000

Data Index: 587432 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8913. Min Act: -0.0000

Data Index: 872260 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8916. Min Act: -0.0000

Data Index: 338603 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1529569 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8077. Min Act: -0.0000

Data Index: 696650 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1106247 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7347. Min Act: -0.0000

Data Index: 278439 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7096. Min Act: -0.0000

Data Index: 574144 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1213544 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7948. Min Act: -0.0000

Data Index: 352426 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7850. Min Act: -0.0000

Data Index: 733349 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1247518 (C4 (Web Text))

Max Activating Token Index: 651