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

Dataset: The Pile

Neuron 362 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: 3.7583. Min Range: -3.7583

Max Act: 3.7583. Min Act: -0.0000

Data Index: 360668 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.4043. Min Act: -0.0000

Data Index: 695432 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.6000. Min Act: -0.0000

Data Index: 249472 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.4009. Min Act: -0.0000

Data Index: 245677 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.2570. Min Act: -0.0000

Data Index: 132153 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.2774. Min Act: -0.0000

Data Index: 84475 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.3818. Min Act: -0.0000

Data Index: 1176817 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.0789. Min Act: -0.0000

Data Index: 1390811 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.2450. Min Act: -0.0000

Data Index: 622069 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.0214. Min Act: -0.0000

Data Index: 899508 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.1800. Min Act: -0.0000

Data Index: 1894629 (The Pile)

Max Activating Token Index: 426

Text #11

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.3398. Min Act: -0.0000

Data Index: 1904017 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.1148. Min Act: -0.0000

Data Index: 1211479 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.1302. Min Act: -0.0000

Data Index: 1537131 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.0687. Min Act: -0.0000

Data Index: 1216646 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.2298. Min Act: -0.0000

Data Index: 911332 (The Pile)

Max Activating Token Index: 641

Text #16

Max Range: 3.7583. Min Range: -3.7583

Max Act: 2.9428. Min Act: -0.0000

Data Index: 1513796 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.0251. Min Act: -0.0000

Data Index: 212956 (The Pile)

Max Activating Token Index: 423

Text #18

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.0847. Min Act: -0.0000

Data Index: 1561061 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 3.7583. Min Range: -3.7583

Max Act: 3.2109. Min Act: -0.0000

Data Index: 205779 (The Pile)

Max Activating Token Index: 107