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

Dataset: The Pile

Neuron 964 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: 0.4451. Min Range: -0.4451

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1780564 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.4261. Min Act: -0.0000

Data Index: 476772 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3639. Min Act: -0.0000

Data Index: 215540 (The Pile)

Max Activating Token Index: 333

Text #3

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3596. Min Act: -0.0000

Data Index: 456094 (The Pile)

Max Activating Token Index: 135

Text #4

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1620660 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3541. Min Act: -0.0000

Data Index: 803820 (The Pile)

Max Activating Token Index: 804

Text #6

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1074598 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1577805 (The Pile)

Max Activating Token Index: 504

Text #8

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1361184 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3407. Min Act: -0.0000

Data Index: 843379 (The Pile)

Max Activating Token Index: 764

Text #10

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1932600 (The Pile)

Max Activating Token Index: 364

Text #11

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1157137 (The Pile)

Max Activating Token Index: 325

Text #12

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1116218 (The Pile)

Max Activating Token Index: 954

Text #13

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.2997. Min Act: 0.0000

Data Index: 905820 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3064. Min Act: -0.0000

Data Index: 471141 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3228. Min Act: -0.0000

Data Index: 337518 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1683753 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.2826. Min Act: -0.0000

Data Index: 876683 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1993343 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.2880. Min Act: 0.0000

Data Index: 1797108 (The Pile)

Max Activating Token Index: 483