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

Dataset: The Pile

Neuron 597 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: 0.7498. Min Range: -0.7498

Max Act: 0.7498. Min Act: -0.0000

Data Index: 877766 (The Pile)

Max Activating Token Index: 252

Text #1

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1713929 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1020357 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1944315 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6604. Min Act: -0.0000

Data Index: 960390 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1974716 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6510. Min Act: -0.0000

Data Index: 505706 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1577165 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6245. Min Act: -0.0000

Data Index: 675234 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6237. Min Act: -0.0000

Data Index: 139519 (The Pile)

Max Activating Token Index: 659

Text #10

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1694051 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6352. Min Act: -0.0000

Data Index: 666687 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1184116 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.6013. Min Act: -0.0000

Data Index: 330893 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5757. Min Act: -0.0000

Data Index: 977263 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1901204 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1555306 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5471. Min Act: -0.0000

Data Index: 368350 (The Pile)

Max Activating Token Index: 956

Text #18

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5785. Min Act: -0.0000

Data Index: 382755 (The Pile)

Max Activating Token Index: 116

Text #19

Max Range: 0.7498. Min Range: -0.7498

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1925033 (The Pile)

Max Activating Token Index: 57