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

Dataset: The Pile

Neuron 742 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0660. Min Range: -1.0660

Max Act: 1.0660. Min Act: -0.0000

Data Index: 550374 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1545031 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9948. Min Act: -0.0000

Data Index: 663930 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9289. Min Act: -0.0000

Data Index: 353601 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9407. Min Act: -0.0000

Data Index: 988662 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9594. Min Act: -0.0000

Data Index: 985236 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1592981 (The Pile)

Max Activating Token Index: 359

Text #7

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1338142 (The Pile)

Max Activating Token Index: 878

Text #8

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1081275 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.8821. Min Act: -0.0000

Data Index: 168307 (The Pile)

Max Activating Token Index: 321

Text #10

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9429. Min Act: -0.0000

Data Index: 746779 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9113. Min Act: -0.0000

Data Index: 260897 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1589677 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.8988. Min Act: -0.0000

Data Index: 577044 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1812156 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1386991 (The Pile)

Max Activating Token Index: 327

Text #16

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.8778. Min Act: -0.0000

Data Index: 416617 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.8468. Min Act: -0.0000

Data Index: 717803 (The Pile)

Max Activating Token Index: 192

Text #18

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.9010. Min Act: -0.0000

Data Index: 896135 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 1.0660. Min Range: -1.0660

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1159099 (The Pile)

Max Activating Token Index: 503