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

Dataset: The Pile

Neuron 4772 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0382. Min Range: -1.0382

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1887405 (The Pile)

Max Activating Token Index: 468

Text #1

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8058. Min Act: -0.0000

Data Index: 879907 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1038244 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1904185 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8622. Min Act: -0.0000

Data Index: 489246 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1127458 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8329. Min Act: -0.0000

Data Index: 556631 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1443046 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1774721 (The Pile)

Max Activating Token Index: 96

Text #9

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7154. Min Act: -0.0000

Data Index: 837119 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1500224 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1648376 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8568. Min Act: -0.0000

Data Index: 76867 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8139. Min Act: -0.0000

Data Index: 909411 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7112. Min Act: -0.0000

Data Index: 182041 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7123. Min Act: -0.0000

Data Index: 823406 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1891111 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.6542. Min Act: -0.0000

Data Index: 573648 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.6956. Min Act: -0.0000

Data Index: 672350 (The Pile)

Max Activating Token Index: 581

Text #19

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7171. Min Act: -0.0000

Data Index: 810784 (The Pile)

Max Activating Token Index: 252