Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1055 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1829738 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9464. Min Act: -0.0000

Data Index: 791931 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8866. Min Act: -0.0000

Data Index: 317892 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8205. Min Act: -0.0000

Data Index: 445495 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1705429 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1626173 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7669. Min Act: -0.0000

Data Index: 271762 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7886. Min Act: -0.0000

Data Index: 864256 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1419292 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1140622 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1274053 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7542. Min Act: -0.0000

Data Index: 38581 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1607335 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1271413 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7175. Min Act: -0.0000

Data Index: 56290 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7081. Min Act: -0.0000

Data Index: 433245 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1530679 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.6926. Min Act: -0.0000

Data Index: 222831 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1301019 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1748550 (The Pile)

Max Activating Token Index: 915