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

Dataset: The Pile

Neuron 1310 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: 0.6304. Min Range: -0.6304

Max Act: 0.6029. Min Act: -0.0000

Data Index: 953277 (The Pile)

Max Activating Token Index: 546

Text #1

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.6304. Min Act: -0.0000

Data Index: 108694 (The Pile)

Max Activating Token Index: 819

Text #2

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1892697 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4637. Min Act: -0.0000

Data Index: 12640 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4723. Min Act: -0.0000

Data Index: 601877 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4565. Min Act: -0.0000

Data Index: 241643 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4508. Min Act: -0.0000

Data Index: 397956 (The Pile)

Max Activating Token Index: 720

Text #7

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4590. Min Act: -0.0000

Data Index: 293195 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4445. Min Act: -0.0000

Data Index: 722465 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4644. Min Act: -0.0000

Data Index: 4421 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1355888 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3558. Min Act: -0.0000

Data Index: 430058 (The Pile)

Max Activating Token Index: 803

Text #12

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1539622 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3925. Min Act: -0.0000

Data Index: 608820 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1082829 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1637023 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1119882 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.4053. Min Act: -0.0000

Data Index: 385116 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3900. Min Act: -0.0000

Data Index: 161829 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 0.6304. Min Range: -0.6304

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1498028 (The Pile)

Max Activating Token Index: 215