Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 823 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0001

Data Index: 856937 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0567. Min Act: -0.0001

Data Index: 558881 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1918 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0536. Min Act: -0.0001

Data Index: 832219 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1334360 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0445. Min Act: -0.0001

Data Index: 607831 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0462. Min Act: -0.0001

Data Index: 1314870 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0526. Min Act: -0.0001

Data Index: 471896 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1430034 (Python Code)

Max Activating Token Index: 502

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1012715 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0489. Min Act: -0.0001

Data Index: 240967 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0467. Min Act: -0.0001

Data Index: 634872 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0470. Min Act: -0.0001

Data Index: 43978 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0443. Min Act: -0.0001

Data Index: 1278105 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0444. Min Act: -0.0001

Data Index: 770815 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0409. Min Act: -0.0001

Data Index: 538925 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1321222 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0433. Min Act: -0.0001

Data Index: 609524 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1175955 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0424. Min Act: -0.0001

Data Index: 556264 (C4 (Web Text))

Max Activating Token Index: 148