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

Dataset: The Pile

Neuron 2816 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: 0.9700. Min Range: -0.9700

Max Act: 0.9700. Min Act: -0.0000

Data Index: 816189 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1598910 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8557. Min Act: -0.0000

Data Index: 180544 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8562. Min Act: -0.0000

Data Index: 34919 (The Pile)

Max Activating Token Index: 356

Text #4

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1393053 (The Pile)

Max Activating Token Index: 625

Text #5

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1957926 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1880726 (The Pile)

Max Activating Token Index: 292

Text #7

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1211236 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7793. Min Act: -0.0000

Data Index: 609958 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7863. Min Act: -0.0000

Data Index: 318884 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7540. Min Act: -0.0000

Data Index: 349161 (The Pile)

Max Activating Token Index: 161

Text #11

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1911266 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1276735 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7297. Min Act: -0.0000

Data Index: 423313 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7474. Min Act: -0.0000

Data Index: 379940 (The Pile)

Max Activating Token Index: 453

Text #15

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1187214 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7323. Min Act: -0.0000

Data Index: 624213 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7132. Min Act: -0.0000

Data Index: 448502 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1871572 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.9700. Min Range: -0.9700

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1405973 (The Pile)

Max Activating Token Index: 186