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

Dataset: The Pile

Neuron 4886 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.7197. Min Act: -0.0000

Data Index: 357691 (The Pile)

Max Activating Token Index: 943

Text #1

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1575455 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1359648 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1503959 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1227220 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5120. Min Act: -0.0000

Data Index: 219224 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1855570 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.5038. Min Act: 0.0000

Data Index: 1829482 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1172456 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4857. Min Act: -0.0000

Data Index: 736072 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1012841 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1254017 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4449. Min Act: 0.0000

Data Index: 1975629 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1503460 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4355. Min Act: -0.0000

Data Index: 503560 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1872585 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1364651 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1236133 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1842043 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 0.7197. Min Range: -0.7197

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1958789 (The Pile)

Max Activating Token Index: 544