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

Dataset: The Pile

Neuron 3431 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9433. Min Act: -0.0000

Data Index: 709474 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1622586 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1222859 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1803148 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8463. Min Act: -0.0000

Data Index: 752880 (The Pile)

Max Activating Token Index: 320

Text #5

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1597996 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1609576 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1927199 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1123541 (The Pile)

Max Activating Token Index: 20

Text #9

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8562. Min Act: -0.0000

Data Index: 343922 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1611441 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1329395 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7407. Min Act: -0.0000

Data Index: 461272 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1939088 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7823. Min Act: -0.0000

Data Index: 528909 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1004368 (The Pile)

Max Activating Token Index: 179

Text #16

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1705396 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1030144 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7320. Min Act: -0.0000

Data Index: 321463 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8019. Min Act: -0.0000

Data Index: 855909 (The Pile)

Max Activating Token Index: 1004