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

Dataset: The Pile

Neuron 4174 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.6236. Min Act: -0.0000

Data Index: 552252 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 4.0983. Min Range: -4.0983

Max Act: 4.0983. Min Act: -0.0000

Data Index: 1470177 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.4399. Min Act: -0.0000

Data Index: 1148898 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.7360. Min Act: -0.0000

Data Index: 431619 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.6265. Min Act: -0.0000

Data Index: 396536 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.5345. Min Act: -0.0000

Data Index: 1156942 (The Pile)

Max Activating Token Index: 155

Text #6

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.7292. Min Act: -0.0000

Data Index: 60104 (The Pile)

Max Activating Token Index: 595

Text #7

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.4990. Min Act: -0.0000

Data Index: 480620 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.4798. Min Act: -0.0000

Data Index: 1449488 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.3548. Min Act: -0.0000

Data Index: 273129 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.3054. Min Act: -0.0000

Data Index: 1601378 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.5022. Min Act: -0.0000

Data Index: 1586739 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.3712. Min Act: -0.0000

Data Index: 1162541 (The Pile)

Max Activating Token Index: 294

Text #13

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.3586. Min Act: -0.0000

Data Index: 643771 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.3140. Min Act: -0.0000

Data Index: 249328 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.3380. Min Act: -0.0000

Data Index: 198801 (The Pile)

Max Activating Token Index: 308

Text #16

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.3047. Min Act: -0.0000

Data Index: 1267532 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.2774. Min Act: -0.0000

Data Index: 1179520 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.0835. Min Act: -0.0000

Data Index: 1381106 (The Pile)

Max Activating Token Index: 674

Text #19

Max Range: 4.0983. Min Range: -4.0983

Max Act: 3.2131. Min Act: -0.0000

Data Index: 958635 (The Pile)

Max Activating Token Index: 155