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

Dataset: The Pile

Neuron 3569 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3995. Min Act: -0.0000

Data Index: 39167 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3786. Min Act: -0.0000

Data Index: 400195 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3606. Min Act: -0.0000

Data Index: 452472 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3745. Min Act: -0.0000

Data Index: 823982 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3654. Min Act: -0.0000

Data Index: 290236 (The Pile)

Max Activating Token Index: 314

Text #5

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1797074 (The Pile)

Max Activating Token Index: 936

Text #6

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1129232 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1492607 (The Pile)

Max Activating Token Index: 254

Text #8

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3205. Min Act: -0.0000

Data Index: 967229 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3342. Min Act: -0.0000

Data Index: 22072 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1963962 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3431. Min Act: -0.0000

Data Index: 197318 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1333015 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3512. Min Act: -0.0000

Data Index: 462495 (The Pile)

Max Activating Token Index: 979

Text #14

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3268. Min Act: -0.0000

Data Index: 306411 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3259. Min Act: -0.0000

Data Index: 94715 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1486620 (The Pile)

Max Activating Token Index: 320

Text #17

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3417. Min Act: -0.0000

Data Index: 626357 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1609644 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1117706 (The Pile)

Max Activating Token Index: 364