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

Dataset: The Pile

Neuron 2457 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: 0.9849. Min Range: -0.9849

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1805417 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.9849. Min Act: -0.0000

Data Index: 279421 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1493114 (The Pile)

Max Activating Token Index: 712

Text #3

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1364988 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8528. Min Act: -0.0000

Data Index: 329467 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8567. Min Act: -0.0000

Data Index: 350840 (The Pile)

Max Activating Token Index: 377

Text #6

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8009. Min Act: -0.0000

Data Index: 878464 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1119910 (The Pile)

Max Activating Token Index: 596

Text #8

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1376115 (The Pile)

Max Activating Token Index: 119

Text #9

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1410063 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7854. Min Act: -0.0000

Data Index: 524195 (The Pile)

Max Activating Token Index: 988

Text #11

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8061. Min Act: -0.0000

Data Index: 350208 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7985. Min Act: -0.0000

Data Index: 354849 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7702. Min Act: -0.0000

Data Index: 763076 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7720. Min Act: -0.0000

Data Index: 582358 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7315. Min Act: -0.0000

Data Index: 564255 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7109. Min Act: -0.0000

Data Index: 765993 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7351. Min Act: -0.0000

Data Index: 246307 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1590693 (The Pile)

Max Activating Token Index: 767

Text #19

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7184. Min Act: -0.0000

Data Index: 881483 (The Pile)

Max Activating Token Index: 181