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

Dataset: The Pile

Neuron 3110 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.8763. Min Act: -0.0000

Data Index: 871671 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.8764. Min Act: -0.0000

Data Index: 892081 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7462. Min Act: -0.0000

Data Index: 207567 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7107. Min Act: -0.0000

Data Index: 259852 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1197227 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1611517 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1038981 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.7277. Min Act: -0.0000

Data Index: 842107 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6401. Min Act: 0.0000

Data Index: 1945660 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1471265 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6373. Min Act: 0.0000

Data Index: 1096003 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6633. Min Act: -0.0000

Data Index: 730957 (The Pile)

Max Activating Token Index: 102

Text #12

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6444. Min Act: -0.0000

Data Index: 411383 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6344. Min Act: 0.0000

Data Index: 653086 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5829. Min Act: -0.0000

Data Index: 747447 (The Pile)

Max Activating Token Index: 810

Text #15

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1729193 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.6074. Min Act: -0.0000

Data Index: 527503 (The Pile)

Max Activating Token Index: 859

Text #17

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1190674 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1818790 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 0.8764. Min Range: -0.8764

Max Act: 0.5516. Min Act: 0.0000

Data Index: 958211 (The Pile)

Max Activating Token Index: 590