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

Dataset: The Pile

Neuron 5044 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: 0.1304. Min Range: -0.1304

Max Act: 0.1304. Min Act: -0.0000

Data Index: 865563 (The Pile)

Max Activating Token Index: 740

Text #1

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1527176 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1951545 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1522161 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1967242 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0972. Min Act: -0.0000

Data Index: 590342 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0959. Min Act: -0.0000

Data Index: 679925 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0803. Min Act: -0.0000

Data Index: 268566 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1550631 (The Pile)

Max Activating Token Index: 507

Text #9

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1270531 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0683. Min Act: -0.0000

Data Index: 464848 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1725998 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1733507 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1508393 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1713265 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1650049 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1442945 (The Pile)

Max Activating Token Index: 597

Text #17

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0761. Min Act: -0.0000

Data Index: 325664 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0767. Min Act: -0.0000

Data Index: 147311 (The Pile)

Max Activating Token Index: 426

Text #19

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.0692. Min Act: -0.0000

Data Index: 117066 (The Pile)

Max Activating Token Index: 131