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

Dataset: The Pile

Neuron 3847 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.9639. Min Act: -0.0000

Data Index: 1584746 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.8430. Min Act: -0.0000

Data Index: 1818838 (The Pile)

Max Activating Token Index: 645

Text #2

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.7778. Min Act: -0.0000

Data Index: 144159 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.6265. Min Act: -0.0000

Data Index: 187917 (The Pile)

Max Activating Token Index: 855

Text #4

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.5900. Min Act: -0.0000

Data Index: 388759 (The Pile)

Max Activating Token Index: 975

Text #5

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.5726. Min Act: -0.0000

Data Index: 1871607 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.4597. Min Act: -0.0000

Data Index: 1525037 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.5547. Min Act: -0.0000

Data Index: 688906 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.5101. Min Act: -0.0000

Data Index: 673199 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.4263. Min Act: -0.0000

Data Index: 782899 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.5310. Min Act: -0.0000

Data Index: 897803 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.4279. Min Act: -0.0000

Data Index: 431322 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.4982. Min Act: -0.0000

Data Index: 452748 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.4952. Min Act: -0.0000

Data Index: 1299779 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.4098. Min Act: -0.0000

Data Index: 483759 (The Pile)

Max Activating Token Index: 897

Text #15

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.2277. Min Act: -0.0000

Data Index: 18540 (The Pile)

Max Activating Token Index: 841

Text #16

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.3230. Min Act: -0.0000

Data Index: 520903 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1303523 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.2921. Min Act: -0.0000

Data Index: 163191 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 1.9639. Min Range: -1.9639

Max Act: 1.2976. Min Act: -0.0000

Data Index: 1259689 (The Pile)

Max Activating Token Index: 472