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

Dataset: The Pile

Neuron 659 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: 5.4199. Min Range: -5.4199

Max Act: 5.4199. Min Act: -0.0000

Data Index: 175541 (The Pile)

Max Activating Token Index: 649

Text #1

Max Range: 5.4199. Min Range: -5.4199

Max Act: 4.7155. Min Act: -0.0000

Data Index: 1801335 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 5.4199. Min Range: -5.4199

Max Act: 4.1626. Min Act: -0.0000

Data Index: 234257 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 5.4199. Min Range: -5.4199

Max Act: 3.2532. Min Act: -0.0000

Data Index: 1636608 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 5.4199. Min Range: -5.4199

Max Act: 4.0891. Min Act: -0.0000

Data Index: 1523260 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 5.4199. Min Range: -5.4199

Max Act: 3.5137. Min Act: -0.0000

Data Index: 346014 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 5.4199. Min Range: -5.4199

Max Act: 3.0335. Min Act: -0.0000

Data Index: 1349456 (The Pile)

Max Activating Token Index: 951

Text #7

Max Range: 5.4199. Min Range: -5.4199

Max Act: 2.8565. Min Act: -0.0000

Data Index: 1199050 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 5.4199. Min Range: -5.4199

Max Act: 2.9330. Min Act: -0.0000

Data Index: 1083661 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 5.4199. Min Range: -5.4199

Max Act: 2.8345. Min Act: -0.0000

Data Index: 226322 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 5.4199. Min Range: -5.4199

Max Act: 2.9625. Min Act: -0.0000

Data Index: 1174338 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 5.4199. Min Range: -5.4199

Max Act: 2.8290. Min Act: -0.0000

Data Index: 1721772 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 5.4199. Min Range: -5.4199

Max Act: 2.6848. Min Act: -0.0000

Data Index: 131826 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 5.4199. Min Range: -5.4199

Max Act: 2.1685. Min Act: -0.0000

Data Index: 318513 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 5.4199. Min Range: -5.4199

Max Act: 2.9401. Min Act: -0.0000

Data Index: 22421 (The Pile)

Max Activating Token Index: 724

Text #15

Max Range: 5.4199. Min Range: -5.4199

Max Act: 3.3889. Min Act: -0.0000

Data Index: 188626 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 5.4199. Min Range: -5.4199

Max Act: 3.3405. Min Act: -0.0000

Data Index: 344831 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 5.4199. Min Range: -5.4199

Max Act: 2.7905. Min Act: -0.0000

Data Index: 78979 (The Pile)

Max Activating Token Index: 32

Text #18

Max Range: 5.4199. Min Range: -5.4199

Max Act: 3.4556. Min Act: -0.0000

Data Index: 1178895 (The Pile)

Max Activating Token Index: 652

Text #19

Max Range: 5.4199. Min Range: -5.4199

Max Act: 2.5869. Min Act: -0.0000

Data Index: 1361757 (The Pile)

Max Activating Token Index: 380