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

Dataset: The Pile

Neuron 3876 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4631. Min Range: -5.4631

Max Act: 5.4631. Min Act: -0.0000

Data Index: 84268 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 5.4631. Min Range: -5.4631

Max Act: 4.8538. Min Act: -0.0000

Data Index: 1632203 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.5268. Min Act: -0.0000

Data Index: 278593 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.8217. Min Act: -0.0000

Data Index: 1544589 (The Pile)

Max Activating Token Index: 745

Text #4

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.5979. Min Act: -0.0000

Data Index: 945245 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.8580. Min Act: -0.0000

Data Index: 1626476 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.7052. Min Act: -0.0000

Data Index: 1093829 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.4895. Min Act: -0.0000

Data Index: 749635 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.3025. Min Act: -0.0000

Data Index: 1438772 (The Pile)

Max Activating Token Index: 452

Text #9

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.6907. Min Act: -0.0000

Data Index: 229664 (The Pile)

Max Activating Token Index: 929

Text #10

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.4972. Min Act: -0.0000

Data Index: 822431 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.0472. Min Act: -0.0000

Data Index: 281620 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.3150. Min Act: -0.0000

Data Index: 1295006 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.4096. Min Act: -0.0000

Data Index: 353768 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.2311. Min Act: -0.0000

Data Index: 809725 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.3737. Min Act: -0.0000

Data Index: 1224671 (The Pile)

Max Activating Token Index: 923

Text #16

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.3662. Min Act: -0.0000

Data Index: 847143 (The Pile)

Max Activating Token Index: 272

Text #17

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.3647. Min Act: -0.0000

Data Index: 764191 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.0259. Min Act: -0.0000

Data Index: 1379966 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 5.4631. Min Range: -5.4631

Max Act: 3.1767. Min Act: -0.0000

Data Index: 1331745 (The Pile)

Max Activating Token Index: 35