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

Dataset: The Pile

Neuron 1612 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: 0.4541. Min Range: -0.4541

Max Act: 0.4541. Min Act: -0.0000

Data Index: 466451 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3620. Min Act: -0.0000

Data Index: 900604 (The Pile)

Max Activating Token Index: 663

Text #2

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3694. Min Act: -0.0000

Data Index: 960485 (The Pile)

Max Activating Token Index: 967

Text #3

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3750. Min Act: -0.0000

Data Index: 770306 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1411927 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3552. Min Act: 0.0000

Data Index: 1237330 (The Pile)

Max Activating Token Index: 538

Text #6

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3457. Min Act: 0.0000

Data Index: 1032604 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3348. Min Act: -0.0000

Data Index: 705594 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3226. Min Act: -0.0000

Data Index: 295393 (The Pile)

Max Activating Token Index: 810

Text #9

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3235. Min Act: -0.0000

Data Index: 912525 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3156. Min Act: 0.0000

Data Index: 956243 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3240. Min Act: -0.0000

Data Index: 403976 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3753. Min Act: -0.0000

Data Index: 682075 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1548985 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1519787 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3078. Min Act: -0.0000

Data Index: 616447 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1807457 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1654040 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1501207 (The Pile)

Max Activating Token Index: 512

Text #19

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3183. Min Act: -0.0000

Data Index: 591021 (The Pile)

Max Activating Token Index: 128