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

Dataset: The Pile

Neuron 4256 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: 1.1034. Min Range: -1.1034

Max Act: 1.1034. Min Act: -0.0000

Data Index: 940518 (The Pile)

Max Activating Token Index: 381

Text #1

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1076524 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8834. Min Act: -0.0000

Data Index: 561045 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9646. Min Act: -0.0000

Data Index: 929097 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1457597 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1991797 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8744. Min Act: -0.0000

Data Index: 179470 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.9401. Min Act: -0.0000

Data Index: 116049 (The Pile)

Max Activating Token Index: 789

Text #8

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8341. Min Act: -0.0000

Data Index: 341054 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7859. Min Act: -0.0000

Data Index: 260593 (The Pile)

Max Activating Token Index: 174

Text #10

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1465600 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.8541. Min Act: -0.0000

Data Index: 300300 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1544254 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7478. Min Act: -0.0000

Data Index: 437071 (The Pile)

Max Activating Token Index: 161

Text #14

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1753422 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7465. Min Act: -0.0000

Data Index: 328830 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1846877 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1237481 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7388. Min Act: -0.0000

Data Index: 456325 (The Pile)

Max Activating Token Index: 355

Text #19

Max Range: 1.1034. Min Range: -1.1034

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1503078 (The Pile)

Max Activating Token Index: 243