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

Dataset: The Pile

Neuron 709 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0601. Min Range: -1.0601

Max Act: 1.0384. Min Act: -0.0000

Data Index: 784863 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 1.0601. Min Range: -1.0601

Max Act: 1.0600. Min Act: -0.0001

Data Index: 1588535 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 1.0601. Min Range: -1.0601

Max Act: 1.0513. Min Act: -0.0000

Data Index: 882137 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9464. Min Act: -0.0000

Data Index: 136096 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 1.0601. Min Range: -1.0601

Max Act: 1.0601. Min Act: -0.0000

Data Index: 789285 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9600. Min Act: -0.0000

Data Index: 514142 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1305571 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1744355 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 1.0601. Min Range: -1.0601

Max Act: 1.0408. Min Act: -0.0000

Data Index: 1477857 (The Pile)

Max Activating Token Index: 751

Text #9

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.8556. Min Act: -0.0000

Data Index: 469991 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1395448 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1751721 (The Pile)

Max Activating Token Index: 524

Text #12

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1748059 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1049760 (The Pile)

Max Activating Token Index: 228

Text #14

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1027354 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1684202 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.8088. Min Act: -0.0000

Data Index: 323506 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1582327 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1669792 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 1.0601. Min Range: -1.0601

Max Act: 0.8761. Min Act: -0.0000

Data Index: 631521 (The Pile)

Max Activating Token Index: 446