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

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

Neuron 1091 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.7549. Min Act: -0.0000

Data Index: 1348071 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.4737. Min Act: -0.0000

Data Index: 234504 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.2711. Min Act: -0.0000

Data Index: 365773 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.6298. Min Act: -0.0000

Data Index: 685994 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.2087. Min Act: -0.0000

Data Index: 142993 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.1125. Min Act: -0.0000

Data Index: 441847 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.4239. Min Act: -0.0000

Data Index: 399322 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.2141. Min Act: -0.0000

Data Index: 854337 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.2171. Min Act: -0.0000

Data Index: 246475 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 4.7549. Min Range: -4.7549

Max Act: 3.8067. Min Act: -0.0000

Data Index: 828479 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 4.7549. Min Range: -4.7549

Max Act: 3.9078. Min Act: -0.0000

Data Index: 1143608 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.0751. Min Act: -0.0000

Data Index: 266499 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 4.7549. Min Range: -4.7549

Max Act: 3.9130. Min Act: -0.0000

Data Index: 820936 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 4.7549. Min Range: -4.7549

Max Act: 3.8937. Min Act: -0.0000

Data Index: 711766 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.5728. Min Act: -0.0000

Data Index: 566853 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.2287. Min Act: -0.0000

Data Index: 724138 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 4.7549. Min Range: -4.7549

Max Act: 3.9704. Min Act: -0.0000

Data Index: 1000772 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 4.7549. Min Range: -4.7549

Max Act: 4.0800. Min Act: -0.0000

Data Index: 1144991 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 4.7549. Min Range: -4.7549

Max Act: 3.7039. Min Act: -0.0000

Data Index: 854452 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 4.7549. Min Range: -4.7549

Max Act: 3.5019. Min Act: -0.0000

Data Index: 460122 (C4 (Web Text))

Max Activating Token Index: 805