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

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

Neuron 2729 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.8074. Min Act: -0.0001

Data Index: 748013 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.7803. Min Act: -0.0000

Data Index: 72448 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6777. Min Act: -0.0000

Data Index: 598958 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1227659 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.7425. Min Act: -0.0000

Data Index: 72416 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.7638. Min Act: -0.0000

Data Index: 932229 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.7094. Min Act: -0.0000

Data Index: 906081 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6897. Min Act: -0.0000

Data Index: 187137 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6686. Min Act: -0.0001

Data Index: 1068743 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1215699 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6261. Min Act: -0.0001

Data Index: 445695 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6439. Min Act: -0.0001

Data Index: 554083 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6416. Min Act: -0.0000

Data Index: 883187 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5973. Min Act: -0.0001

Data Index: 157126 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6133. Min Act: -0.0000

Data Index: 961152 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5947. Min Act: -0.0000

Data Index: 599908 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6202. Min Act: -0.0000

Data Index: 121275 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6285. Min Act: -0.0000

Data Index: 98767 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.6075. Min Act: -0.0001

Data Index: 1301958 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.8074. Min Range: -0.8074

Max Act: 0.5419. Min Act: -0.0000

Data Index: 563218 (C4 (Web Text))

Max Activating Token Index: 802