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

Dataset: The Pile

Neuron 1883 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.3147. Min Act: -0.0000

Data Index: 691676 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9693. Min Act: -0.0000

Data Index: 486328 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.9523. Min Act: -0.0000

Data Index: 741646 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.8682. Min Act: -0.0000

Data Index: 114087 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.7676. Min Act: -0.0000

Data Index: 736113 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.7408. Min Act: -0.0000

Data Index: 296482 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.5629. Min Act: -0.0000

Data Index: 610891 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1389953 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6139. Min Act: -0.0000

Data Index: 751202 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1687115 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1003305 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6449. Min Act: -0.0000

Data Index: 660321 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1620289 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6033. Min Act: -0.0000

Data Index: 358417 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1299335 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.5954. Min Act: -0.0000

Data Index: 872247 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6576. Min Act: -0.0000

Data Index: 949905 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1807808 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.5632. Min Act: -0.0000

Data Index: 939833 (The Pile)

Max Activating Token Index: 447

Text #19

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1945536 (The Pile)

Max Activating Token Index: 455