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

Dataset: The Pile

Neuron 1108 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: 0.9469. Min Range: -0.9469

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1180553 (The Pile)

Max Activating Token Index: 363

Text #1

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1637568 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1260694 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8153. Min Act: -0.0000

Data Index: 740572 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.8524. Min Act: -0.0000

Data Index: 661491 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6996. Min Act: -0.0000

Data Index: 142553 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7815. Min Act: -0.0000

Data Index: 451988 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1459311 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7739. Min Act: -0.0000

Data Index: 589261 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7735. Min Act: -0.0000

Data Index: 428284 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6864. Min Act: -0.0000

Data Index: 592554 (The Pile)

Max Activating Token Index: 168

Text #11

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.7402. Min Act: -0.0000

Data Index: 850575 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1701493 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1520222 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1096274 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6253. Min Act: -0.0000

Data Index: 111591 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1966933 (The Pile)

Max Activating Token Index: 166

Text #17

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6622. Min Act: -0.0000

Data Index: 435593 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6156. Min Act: -0.0000

Data Index: 539912 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.9469. Min Range: -0.9469

Max Act: 0.6574. Min Act: -0.0000

Data Index: 58019 (The Pile)

Max Activating Token Index: 789