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

Dataset: The Pile

Neuron 3071 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1408179 (The Pile)

Max Activating Token Index: 717

Text #1

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1588083 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.6869. Min Act: -0.0000

Data Index: 55935 (The Pile)

Max Activating Token Index: 258

Text #3

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8229. Min Act: -0.0000

Data Index: 604239 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8138. Min Act: -0.0000

Data Index: 529818 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.9505. Min Act: -0.0000

Data Index: 613110 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7519. Min Act: -0.0000

Data Index: 549127 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1901782 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7755. Min Act: -0.0000

Data Index: 549182 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1292334 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7737. Min Act: -0.0000

Data Index: 855059 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8491. Min Act: -0.0000

Data Index: 724526 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1359315 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.8244. Min Act: -0.0000

Data Index: 536413 (The Pile)

Max Activating Token Index: 236

Text #14

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7218. Min Act: -0.0000

Data Index: 286852 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1739531 (The Pile)

Max Activating Token Index: 130

Text #16

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1548908 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7060. Min Act: -0.0000

Data Index: 378634 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1576569 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 0.9505. Min Range: -0.9505

Max Act: 0.7158. Min Act: -0.0000

Data Index: 361265 (The Pile)

Max Activating Token Index: 449