Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3576 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.5177. Min Act: -0.0000

Data Index: 853110 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.5458. Min Act: -0.0000

Data Index: 860696 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.4183. Min Act: -0.0000

Data Index: 303037 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.2345. Min Act: -0.0000

Data Index: 984252 (The Pile)

Max Activating Token Index: 59

Text #4

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3831. Min Act: -0.0000

Data Index: 1368288 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.3740. Min Act: -0.0000

Data Index: 1290851 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1928476 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.4298. Min Act: -0.0000

Data Index: 206749 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.2130. Min Act: -0.0000

Data Index: 894300 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1187433 (The Pile)

Max Activating Token Index: 508

Text #10

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.1481. Min Act: -0.0000

Data Index: 559849 (The Pile)

Max Activating Token Index: 360

Text #11

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.1247. Min Act: -0.0000

Data Index: 775121 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1617002 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1493041 (The Pile)

Max Activating Token Index: 911

Text #14

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1617710 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 1.5458. Min Range: -1.5458

Max Act: 0.9933. Min Act: -0.0000

Data Index: 986253 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 1.5458. Min Range: -1.5458

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1429858 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 1.5458. Min Range: -1.5458

Max Act: 0.9680. Min Act: -0.0000

Data Index: 413829 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 1.5458. Min Range: -1.5458

Max Act: 0.9849. Min Act: -0.0000

Data Index: 137533 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 1.5458. Min Range: -1.5458

Max Act: 1.0699. Min Act: -0.0000

Data Index: 871271 (The Pile)

Max Activating Token Index: 54