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

Dataset: The Pile

Neuron 3865 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: 1.9816. Min Range: -1.9816

Max Act: 1.9408. Min Act: -0.0000

Data Index: 1643087 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.9133. Min Act: -0.0000

Data Index: 1795993 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.7734. Min Act: -0.0000

Data Index: 132704 (The Pile)

Max Activating Token Index: 871

Text #3

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.9816. Min Act: -0.0000

Data Index: 977278 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.8377. Min Act: -0.0000

Data Index: 740743 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.7012. Min Act: -0.0000

Data Index: 1561019 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.7846. Min Act: -0.0000

Data Index: 29192 (The Pile)

Max Activating Token Index: 241

Text #7

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.7618. Min Act: -0.0000

Data Index: 11624 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.5571. Min Act: -0.0000

Data Index: 1798706 (The Pile)

Max Activating Token Index: 800

Text #9

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.6355. Min Act: -0.0000

Data Index: 686834 (The Pile)

Max Activating Token Index: 873

Text #10

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.6704. Min Act: -0.0000

Data Index: 990312 (The Pile)

Max Activating Token Index: 548

Text #11

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1828253 (The Pile)

Max Activating Token Index: 810

Text #12

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.5740. Min Act: -0.0000

Data Index: 1388127 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1965278 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.4436. Min Act: -0.0000

Data Index: 1409359 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1205738 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.6138. Min Act: -0.0000

Data Index: 1252995 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.4174. Min Act: -0.0000

Data Index: 918531 (The Pile)

Max Activating Token Index: 57

Text #18

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.4927. Min Act: -0.0000

Data Index: 1595597 (The Pile)

Max Activating Token Index: 410

Text #19

Max Range: 1.9816. Min Range: -1.9816

Max Act: 1.5031. Min Act: -0.0000

Data Index: 44836 (The Pile)

Max Activating Token Index: 987