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

Dataset: The Pile

Neuron 4204 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: 0.7175. Min Range: -0.7175

Max Act: 0.7175. Min Act: -0.0000

Data Index: 889 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1173486 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1442968 (The Pile)

Max Activating Token Index: 260

Text #3

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.6425. Min Act: -0.0000

Data Index: 994210 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.6335. Min Act: -0.0000

Data Index: 883352 (The Pile)

Max Activating Token Index: 150

Text #5

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1867128 (The Pile)

Max Activating Token Index: 750

Text #6

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1904546 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.5944. Min Act: -0.0000

Data Index: 899127 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1319728 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1410460 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1305623 (The Pile)

Max Activating Token Index: 583

Text #11

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.5452. Min Act: -0.0000

Data Index: 58667 (The Pile)

Max Activating Token Index: 921

Text #12

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.6387. Min Act: -0.0000

Data Index: 13015 (The Pile)

Max Activating Token Index: 525

Text #13

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.5667. Min Act: -0.0000

Data Index: 991194 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1678483 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.4669. Min Act: -0.0000

Data Index: 269628 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1183649 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1422797 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1116723 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 0.7175. Min Range: -0.7175

Max Act: 0.3855. Min Act: -0.0000

Data Index: 590522 (The Pile)

Max Activating Token Index: 616