Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3604 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0548. Min Range: -1.0548

Max Act: 1.0548. Min Act: -0.0001

Data Index: 171364 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.8882. Min Act: -0.0001

Data Index: 1245923 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.8013. Min Act: -0.0001

Data Index: 1081139 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.8144. Min Act: -0.0001

Data Index: 126019 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.7724. Min Act: -0.0001

Data Index: 397626 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.7670. Min Act: -0.0001

Data Index: 1210578 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.7539. Min Act: -0.0001

Data Index: 886368 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.7567. Min Act: -0.0001

Data Index: 876491 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.6763. Min Act: -0.0001

Data Index: 98444 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.7053. Min Act: -0.0001

Data Index: 169200 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.7473. Min Act: -0.0001

Data Index: 578996 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.7111. Min Act: -0.0001

Data Index: 206889 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.7164. Min Act: -0.0001

Data Index: 1225174 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.6927. Min Act: -0.0001

Data Index: 1348688 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1080590 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.6710. Min Act: -0.0001

Data Index: 745389 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.6382. Min Act: -0.0001

Data Index: 264374 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.6548. Min Act: -0.0001

Data Index: 100801 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.6748. Min Act: -0.0001

Data Index: 1062264 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 1.0548. Min Range: -1.0548

Max Act: 0.6527. Min Act: -0.0001

Data Index: 524182 (C4 (Web Text))

Max Activating Token Index: 229