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

Dataset: The Pile

Neuron 4596 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4161. Min Range: -4.4161

Max Act: 4.4161. Min Act: -0.0000

Data Index: 966725 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 4.4161. Min Range: -4.4161

Max Act: 3.3033. Min Act: -0.0000

Data Index: 1526303 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 4.4161. Min Range: -4.4161

Max Act: 3.1038. Min Act: -0.0000

Data Index: 1980317 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 4.4161. Min Range: -4.4161

Max Act: 3.1515. Min Act: -0.0000

Data Index: 236240 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.7976. Min Act: -0.0000

Data Index: 1404861 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.7619. Min Act: -0.0000

Data Index: 838702 (The Pile)

Max Activating Token Index: 287

Text #6

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.5986. Min Act: -0.0000

Data Index: 882848 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.3888. Min Act: -0.0000

Data Index: 1463640 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.3219. Min Act: -0.0000

Data Index: 297622 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.4273. Min Act: -0.0000

Data Index: 536768 (The Pile)

Max Activating Token Index: 394

Text #10

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.2065. Min Act: -0.0000

Data Index: 683766 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.1717. Min Act: -0.0000

Data Index: 593931 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.0738. Min Act: -0.0000

Data Index: 1502906 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.4079. Min Act: -0.0000

Data Index: 775516 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.2134. Min Act: -0.0000

Data Index: 1985527 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.1417. Min Act: -0.0000

Data Index: 1458148 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.0728. Min Act: -0.0000

Data Index: 742370 (The Pile)

Max Activating Token Index: 727

Text #17

Max Range: 4.4161. Min Range: -4.4161

Max Act: 1.9794. Min Act: -0.0000

Data Index: 1514624 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 4.4161. Min Range: -4.4161

Max Act: 2.0743. Min Act: -0.0000

Data Index: 1713592 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 4.4161. Min Range: -4.4161

Max Act: 1.9859. Min Act: -0.0000

Data Index: 905687 (The Pile)

Max Activating Token Index: 576