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

Dataset: The Pile

Neuron 758 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.9508. Min Act: -0.0000

Data Index: 503261 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8595. Min Act: -0.0000

Data Index: 37126 (The Pile)

Max Activating Token Index: 621

Text #2

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8894. Min Act: -0.0000

Data Index: 634036 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8673. Min Act: -0.0000

Data Index: 928332 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8700. Min Act: 0.0000

Data Index: 100182 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8335. Min Act: -0.0000

Data Index: 208851 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7996. Min Act: -0.0000

Data Index: 591912 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1877789 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1514302 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1217666 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1800003 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1888046 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8077. Min Act: -0.0000

Data Index: 760654 (The Pile)

Max Activating Token Index: 1001

Text #13

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7554. Min Act: -0.0000

Data Index: 533527 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1859331 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7861. Min Act: -0.0000

Data Index: 860893 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7352. Min Act: -0.0000

Data Index: 393355 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1077447 (The Pile)

Max Activating Token Index: 979

Text #18

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1079071 (The Pile)

Max Activating Token Index: 750

Text #19

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1549678 (The Pile)

Max Activating Token Index: 559