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

Dataset: The Pile

Neuron 1872 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1906790 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1116312 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1400615 (The Pile)

Max Activating Token Index: 516

Text #3

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4726. Min Act: -0.0000

Data Index: 572213 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1050881 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4258. Min Act: -0.0000

Data Index: 784127 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1739483 (The Pile)

Max Activating Token Index: 478

Text #7

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5105. Min Act: 0.0000

Data Index: 1836989 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4522. Min Act: -0.0000

Data Index: 686714 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1387551 (The Pile)

Max Activating Token Index: 208

Text #10

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4657. Min Act: -0.0000

Data Index: 630737 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.5880. Min Act: -0.0000

Data Index: 57003 (The Pile)

Max Activating Token Index: 526

Text #12

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1709233 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4979. Min Act: -0.0000

Data Index: 4611 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1881666 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1424626 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4640. Min Act: -0.0000

Data Index: 879189 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1881514 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4511. Min Act: -0.0000

Data Index: 992766 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 0.5944. Min Range: -0.5944

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1875669 (The Pile)

Max Activating Token Index: 662