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

Dataset: The Pile

Neuron 4026 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: 1.3911. Min Range: -1.3911

Max Act: 1.3667. Min Act: -0.0000

Data Index: 1612143 (The Pile)

Max Activating Token Index: 934

Text #1

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.3911. Min Act: -0.0000

Data Index: 24108 (The Pile)

Max Activating Token Index: 858

Text #2

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1938. Min Act: -0.0000

Data Index: 996204 (The Pile)

Max Activating Token Index: 719

Text #3

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.3379. Min Act: -0.0000

Data Index: 469408 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1840. Min Act: -0.0000

Data Index: 1586789 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2089. Min Act: -0.0000

Data Index: 78259 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1418457 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.3712. Min Act: -0.0000

Data Index: 284578 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1092910 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1702130 (The Pile)

Max Activating Token Index: 453

Text #10

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1939. Min Act: -0.0000

Data Index: 241614 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1420. Min Act: -0.0000

Data Index: 922281 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1694242 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1113213 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1716496 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1879. Min Act: -0.0000

Data Index: 850079 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1040208 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 1.3911. Min Range: -1.3911

Max Act: 0.9714. Min Act: -0.0000

Data Index: 345025 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.0342. Min Act: -0.0000

Data Index: 858510 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 1.3911. Min Range: -1.3911

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1294772 (The Pile)

Max Activating Token Index: 488