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

Dataset: The Pile

Neuron 3675 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1402982 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0458. Min Act: 0.0000

Data Index: 329638 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1984034 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0466. Min Act: -0.0000

Data Index: 602550 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0458. Min Act: 0.0000

Data Index: 1009561 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1579728 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0466. Min Act: -0.0000

Data Index: 571712 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0440. Min Act: -0.0000

Data Index: 606643 (The Pile)

Max Activating Token Index: 746

Text #8

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1904827 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0437. Min Act: -0.0000

Data Index: 1564665 (The Pile)

Max Activating Token Index: 611

Text #10

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0452. Min Act: -0.0000

Data Index: 787905 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0434. Min Act: -0.0000

Data Index: 1294635 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0432. Min Act: -0.0000

Data Index: 659022 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0431. Min Act: -0.0000

Data Index: 1668537 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0428. Min Act: -0.0000

Data Index: 341875 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0425. Min Act: -0.0000

Data Index: 1251804 (The Pile)

Max Activating Token Index: 61

Text #16

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0423. Min Act: -0.0000

Data Index: 1281231 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0421. Min Act: -0.0000

Data Index: 6057 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0419. Min Act: -0.0000

Data Index: 301558 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0405. Min Act: -0.0000

Data Index: 4839 (The Pile)

Max Activating Token Index: 798