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

Dataset: The Pile

Neuron 1609 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: 1.3967. Min Range: -1.3967

Max Act: 1.3402. Min Act: -0.0000

Data Index: 1463260 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.3516. Min Act: -0.0000

Data Index: 106429 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.3967. Min Act: 0.0000

Data Index: 1532181 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.3141. Min Act: -0.0000

Data Index: 1330604 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.1182. Min Act: -0.0000

Data Index: 222650 (The Pile)

Max Activating Token Index: 608

Text #5

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0799. Min Act: -0.0000

Data Index: 74351 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.9435. Min Act: -0.0000

Data Index: 523943 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0765. Min Act: -0.0000

Data Index: 358828 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1636542 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0916. Min Act: -0.0000

Data Index: 1751641 (The Pile)

Max Activating Token Index: 830

Text #10

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.1643. Min Act: -0.0000

Data Index: 1494173 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.1082. Min Act: -0.0000

Data Index: 897739 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.1535. Min Act: -0.0000

Data Index: 873639 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0182. Min Act: -0.0000

Data Index: 125730 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.8522. Min Act: -0.0000

Data Index: 185685 (The Pile)

Max Activating Token Index: 708

Text #15

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.1110. Min Act: -0.0000

Data Index: 1983889 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1686480 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0620. Min Act: -0.0000

Data Index: 157106 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.0447. Min Act: -0.0000

Data Index: 88624 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.8744. Min Act: -0.0000

Data Index: 286362 (The Pile)

Max Activating Token Index: 545