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

Dataset: The Pile

Neuron 336 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: 8.7728. Min Range: -8.7728

Max Act: 8.7728. Min Act: -0.0000

Data Index: 1426978 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 8.7728. Min Range: -8.7728

Max Act: 8.4216. Min Act: -0.0000

Data Index: 915454 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 8.7728. Min Range: -8.7728

Max Act: 8.1033. Min Act: -0.0000

Data Index: 1262931 (The Pile)

Max Activating Token Index: 166

Text #3

Max Range: 8.7728. Min Range: -8.7728

Max Act: 8.4428. Min Act: -0.0000

Data Index: 1044568 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 8.7728. Min Range: -8.7728

Max Act: 8.0330. Min Act: -0.0000

Data Index: 1793289 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.5732. Min Act: -0.0000

Data Index: 188189 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.9498. Min Act: -0.0000

Data Index: 895446 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 8.7728. Min Range: -8.7728

Max Act: 8.0538. Min Act: -0.0000

Data Index: 1954500 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 8.7728. Min Range: -8.7728

Max Act: 8.0663. Min Act: -0.0000

Data Index: 1442115 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.9888. Min Act: -0.0000

Data Index: 590055 (The Pile)

Max Activating Token Index: 501

Text #10

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.9692. Min Act: -0.0000

Data Index: 1001216 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.9272. Min Act: -0.0000

Data Index: 991536 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.6797. Min Act: -0.0000

Data Index: 185549 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.6748. Min Act: -0.0000

Data Index: 1127436 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.9819. Min Act: -0.0000

Data Index: 396156 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.9762. Min Act: -0.0000

Data Index: 458475 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.9518. Min Act: -0.0000

Data Index: 1900705 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.5681. Min Act: -0.0000

Data Index: 442034 (The Pile)

Max Activating Token Index: 54

Text #18

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.7359. Min Act: -0.0000

Data Index: 1435523 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 8.7728. Min Range: -8.7728

Max Act: 7.5390. Min Act: -0.0000

Data Index: 532873 (The Pile)

Max Activating Token Index: 74