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

Dataset: The Pile

Neuron 2932 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3717. Min Range: -5.3717

Max Act: 5.3717. Min Act: -0.0000

Data Index: 358550 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.8672. Min Act: -0.0000

Data Index: 91561 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.8904. Min Act: -0.0000

Data Index: 307477 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.9742. Min Act: -0.0000

Data Index: 308613 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 5.3717. Min Range: -5.3717

Max Act: 5.0789. Min Act: -0.0000

Data Index: 1470658 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.8781. Min Act: -0.0000

Data Index: 1952016 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.8416. Min Act: -0.0000

Data Index: 745873 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.9672. Min Act: -0.0000

Data Index: 1742420 (The Pile)

Max Activating Token Index: 159

Text #8

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.7380. Min Act: -0.0000

Data Index: 1198368 (The Pile)

Max Activating Token Index: 452

Text #9

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.6858. Min Act: -0.0000

Data Index: 496163 (The Pile)

Max Activating Token Index: 453

Text #10

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.5400. Min Act: -0.0000

Data Index: 1482103 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.7842. Min Act: -0.0000

Data Index: 404496 (The Pile)

Max Activating Token Index: 689

Text #12

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.6561. Min Act: -0.0000

Data Index: 1514600 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.5217. Min Act: -0.0000

Data Index: 1307535 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.4593. Min Act: -0.0000

Data Index: 1498095 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.4568. Min Act: -0.0000

Data Index: 843733 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.4465. Min Act: -0.0000

Data Index: 1910651 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.2550. Min Act: -0.0000

Data Index: 564818 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.2009. Min Act: -0.0000

Data Index: 832210 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 5.3717. Min Range: -5.3717

Max Act: 4.3526. Min Act: -0.0000

Data Index: 838726 (The Pile)

Max Activating Token Index: 453