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

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

Neuron 4051 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: 1.4015. Min Range: -1.4015

Max Act: 1.3282. Min Act: -0.0001

Data Index: 1019072 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.3839. Min Act: -0.0001

Data Index: 482074 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.3121. Min Act: -0.0001

Data Index: 1012580 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.4015. Min Act: -0.0001

Data Index: 245293 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.2561. Min Act: -0.0001

Data Index: 1167577 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.2489. Min Act: -0.0001

Data Index: 872187 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.1729. Min Act: -0.0001

Data Index: 419593 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.1666. Min Act: -0.0001

Data Index: 413417 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.1603. Min Act: -0.0001

Data Index: 1254149 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.1359. Min Act: -0.0001

Data Index: 97668 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.0927. Min Act: -0.0001

Data Index: 678858 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.1232. Min Act: -0.0001

Data Index: 1046124 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.0758. Min Act: -0.0001

Data Index: 394621 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.0738. Min Act: -0.0001

Data Index: 1304981 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.0648. Min Act: -0.0001

Data Index: 420268 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.1627. Min Act: -0.0001

Data Index: 524242 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.0434. Min Act: -0.0001

Data Index: 663920 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.0614. Min Act: -0.0001

Data Index: 1303835 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.1244. Min Act: -0.0001

Data Index: 605527 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 1.4015. Min Range: -1.4015

Max Act: 1.0542. Min Act: -0.0001

Data Index: 145620 (C4 (Web Text))

Max Activating Token Index: 983