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

Dataset: The Pile

Neuron 4569 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1583616 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1874105 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1953748 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.6678. Min Act: -0.0000

Data Index: 854529 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1789151 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5539. Min Act: -0.0000

Data Index: 690169 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1526125 (The Pile)

Max Activating Token Index: 545

Text #7

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5484. Min Act: -0.0000

Data Index: 910401 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5228. Min Act: -0.0000

Data Index: 922187 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5907. Min Act: -0.0000

Data Index: 517833 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5341. Min Act: -0.0000

Data Index: 298782 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5227. Min Act: -0.0000

Data Index: 543145 (The Pile)

Max Activating Token Index: 474

Text #12

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1938099 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.4707. Min Act: 0.0000

Data Index: 519458 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1556487 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1333252 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1593670 (The Pile)

Max Activating Token Index: 119

Text #17

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.5011. Min Act: -0.0000

Data Index: 521930 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.4786. Min Act: -0.0000

Data Index: 676479 (The Pile)

Max Activating Token Index: 379

Text #19

Max Range: 0.8942. Min Range: -0.8942

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1162571 (The Pile)

Max Activating Token Index: 671