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

Dataset: The Pile

Neuron 4780 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.4439. Min Act: -0.0000

Data Index: 649503 (The Pile)

Max Activating Token Index: 363

Text #1

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1626653 (The Pile)

Max Activating Token Index: 452

Text #2

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.1830. Min Act: -0.0000

Data Index: 1059266 (The Pile)

Max Activating Token Index: 403

Text #3

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.2669. Min Act: -0.0000

Data Index: 369290 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.2254. Min Act: -0.0000

Data Index: 1160376 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.1633. Min Act: -0.0000

Data Index: 960868 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.0560. Min Act: -0.0000

Data Index: 210621 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1566185 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1493345 (The Pile)

Max Activating Token Index: 158

Text #9

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1747428 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.1007. Min Act: -0.0000

Data Index: 895717 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1599477 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 1.4439. Min Range: -1.4439

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1490289 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1868219 (The Pile)

Max Activating Token Index: 366

Text #14

Max Range: 1.4439. Min Range: -1.4439

Max Act: 0.9927. Min Act: -0.0000

Data Index: 108910 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 1.4439. Min Range: -1.4439

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1941099 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.0302. Min Act: -0.0000

Data Index: 1292143 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 1.4439. Min Range: -1.4439

Max Act: 1.0325. Min Act: -0.0000

Data Index: 470619 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 1.4439. Min Range: -1.4439

Max Act: 0.9937. Min Act: -0.0000

Data Index: 1691588 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 1.4439. Min Range: -1.4439

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1458275 (The Pile)

Max Activating Token Index: 236