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

Dataset: The Pile

Neuron 3553 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0433. Min Range: -1.0433

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1901968 (The Pile)

Max Activating Token Index: 224

Text #1

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1206043 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1661113 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1312790 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1475751 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.7646. Min Act: -0.0000

Data Index: 581866 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.7814. Min Act: -0.0000

Data Index: 389092 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1128130 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.7467. Min Act: -0.0000

Data Index: 600354 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.7672. Min Act: -0.0000

Data Index: 605040 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1470464 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.7445. Min Act: -0.0000

Data Index: 850779 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.7361. Min Act: -0.0000

Data Index: 730938 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.6634. Min Act: -0.0000

Data Index: 855633 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.7397. Min Act: -0.0000

Data Index: 833502 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.7349. Min Act: -0.0000

Data Index: 195224 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1000781 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1468215 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1110544 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 1.0433. Min Range: -1.0433

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1488789 (The Pile)

Max Activating Token Index: 253