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

Dataset: The Pile

Neuron 3185 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: 5.3145. Min Range: -5.3145

Max Act: 5.3145. Min Act: -0.0000

Data Index: 420130 (The Pile)

Max Activating Token Index: 379

Text #1

Max Range: 5.3145. Min Range: -5.3145

Max Act: 4.5645. Min Act: -0.0000

Data Index: 1638642 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 5.3145. Min Range: -5.3145

Max Act: 3.5121. Min Act: -0.0000

Data Index: 1391205 (The Pile)

Max Activating Token Index: 435

Text #3

Max Range: 5.3145. Min Range: -5.3145

Max Act: 3.2962. Min Act: -0.0000

Data Index: 1437874 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 5.3145. Min Range: -5.3145

Max Act: 3.5234. Min Act: -0.0000

Data Index: 189530 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 5.3145. Min Range: -5.3145

Max Act: 3.2852. Min Act: -0.0000

Data Index: 78727 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 5.3145. Min Range: -5.3145

Max Act: 3.3693. Min Act: -0.0000

Data Index: 693909 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 5.3145. Min Range: -5.3145

Max Act: 2.9443. Min Act: -0.0000

Data Index: 1062090 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 5.3145. Min Range: -5.3145

Max Act: 3.3147. Min Act: -0.0000

Data Index: 757753 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 5.3145. Min Range: -5.3145

Max Act: 3.0702. Min Act: -0.0000

Data Index: 1160300 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 5.3145. Min Range: -5.3145

Max Act: 3.1487. Min Act: -0.0000

Data Index: 1113230 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 5.3145. Min Range: -5.3145

Max Act: 2.6075. Min Act: -0.0000

Data Index: 224274 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 5.3145. Min Range: -5.3145

Max Act: 2.7028. Min Act: -0.0000

Data Index: 916573 (The Pile)

Max Activating Token Index: 353

Text #13

Max Range: 5.3145. Min Range: -5.3145

Max Act: 2.9751. Min Act: -0.0000

Data Index: 758140 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 5.3145. Min Range: -5.3145

Max Act: 3.0489. Min Act: -0.0000

Data Index: 1244473 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 5.3145. Min Range: -5.3145

Max Act: 2.4447. Min Act: -0.0000

Data Index: 602860 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 5.3145. Min Range: -5.3145

Max Act: 2.9416. Min Act: -0.0000

Data Index: 597296 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 5.3145. Min Range: -5.3145

Max Act: 2.6460. Min Act: -0.0000

Data Index: 975804 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 5.3145. Min Range: -5.3145

Max Act: 2.7221. Min Act: -0.0000

Data Index: 493190 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 5.3145. Min Range: -5.3145

Max Act: 2.5933. Min Act: -0.0000

Data Index: 73485 (The Pile)

Max Activating Token Index: 198