Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2803. Min Range: -1.2803

Max Act: 1.2803. Min Act: -0.0000

Data Index: 980977 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 1.2803. Min Range: -1.2803

Max Act: 1.0403. Min Act: -0.0000

Data Index: 1392893 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8833. Min Act: -0.0000

Data Index: 1621706 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8605. Min Act: -0.0000

Data Index: 267791 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8662. Min Act: -0.0000

Data Index: 621465 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.9000. Min Act: -0.0000

Data Index: 87080 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1130434 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1565355 (The Pile)

Max Activating Token Index: 270

Text #8

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1689934 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1185510 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.7892. Min Act: -0.0000

Data Index: 67478 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.7767. Min Act: -0.0000

Data Index: 125382 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.7846. Min Act: -0.0000

Data Index: 929214 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1707236 (The Pile)

Max Activating Token Index: 33

Text #14

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1024716 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.7706. Min Act: -0.0000

Data Index: 293390 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.7217. Min Act: -0.0000

Data Index: 194060 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1116698 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.7337. Min Act: -0.0000

Data Index: 159895 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1340319 (The Pile)

Max Activating Token Index: 371