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

Dataset: The Pile

Neuron 1954 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2629. Min Range: -1.2629

Max Act: 1.2629. Min Act: -0.0000

Data Index: 1425370 (The Pile)

Max Activating Token Index: 287

Text #1

Max Range: 1.2629. Min Range: -1.2629

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1336356 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.9932. Min Act: -0.0000

Data Index: 994722 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 1.2629. Min Range: -1.2629

Max Act: 1.0049. Min Act: -0.0000

Data Index: 458969 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1503009 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.9147. Min Act: -0.0000

Data Index: 67372 (The Pile)

Max Activating Token Index: 423

Text #6

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.9436. Min Act: -0.0000

Data Index: 881453 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1622496 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.8366. Min Act: -0.0000

Data Index: 496439 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1902251 (The Pile)

Max Activating Token Index: 71

Text #10

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1041003 (The Pile)

Max Activating Token Index: 921

Text #11

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1223873 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.8249. Min Act: -0.0000

Data Index: 507390 (The Pile)

Max Activating Token Index: 896

Text #13

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.8643. Min Act: -0.0000

Data Index: 775171 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.8626. Min Act: -0.0000

Data Index: 407987 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.7899. Min Act: -0.0000

Data Index: 171279 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.7597. Min Act: -0.0000

Data Index: 439541 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1255439 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.7393. Min Act: -0.0000

Data Index: 885283 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 1.2629. Min Range: -1.2629

Max Act: 0.7754. Min Act: -0.0000

Data Index: 285510 (The Pile)

Max Activating Token Index: 300