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

Dataset: The Pile

Neuron 3525 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: 1.8572. Min Range: -1.8572

Max Act: 1.8572. Min Act: -0.0000

Data Index: 967223 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.4079. Min Act: -0.0000

Data Index: 1558406 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.5485. Min Act: -0.0000

Data Index: 1862236 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.1537. Min Act: -0.0000

Data Index: 362509 (The Pile)

Max Activating Token Index: 599

Text #4

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.1820. Min Act: -0.0000

Data Index: 1992856 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.4530. Min Act: -0.0000

Data Index: 66071 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3004. Min Act: -0.0000

Data Index: 772831 (The Pile)

Max Activating Token Index: 413

Text #7

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.2697. Min Act: -0.0000

Data Index: 645240 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1023961 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.5352. Min Act: -0.0000

Data Index: 1331630 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.1325. Min Act: -0.0000

Data Index: 1114857 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.4343. Min Act: -0.0000

Data Index: 575605 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3177. Min Act: -0.0000

Data Index: 32340 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.1561. Min Act: -0.0000

Data Index: 566683 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.2790. Min Act: -0.0000

Data Index: 82713 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.2433. Min Act: -0.0000

Data Index: 927397 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.2711. Min Act: -0.0000

Data Index: 156131 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.3005. Min Act: -0.0000

Data Index: 1367410 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1933234 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.1627. Min Act: -0.0000

Data Index: 1254066 (The Pile)

Max Activating Token Index: 980