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

Dataset: The Pile

Neuron 4129 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: 0.5410. Min Range: -0.5410

Max Act: 0.5152. Min Act: -0.0000

Data Index: 86401 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1686643 (The Pile)

Max Activating Token Index: 791

Text #2

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5120. Min Act: -0.0000

Data Index: 141436 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5085. Min Act: -0.0000

Data Index: 799708 (The Pile)

Max Activating Token Index: 295

Text #4

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1155670 (The Pile)

Max Activating Token Index: 950

Text #5

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1359635 (The Pile)

Max Activating Token Index: 736

Text #6

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1099251 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1323187 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1381478 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4424. Min Act: -0.0000

Data Index: 651099 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4385. Min Act: -0.0000

Data Index: 295860 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1121143 (The Pile)

Max Activating Token Index: 487

Text #12

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4363. Min Act: -0.0000

Data Index: 717655 (The Pile)

Max Activating Token Index: 979

Text #13

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1485525 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1127363 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4516. Min Act: -0.0000

Data Index: 419002 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4384. Min Act: -0.0000

Data Index: 550732 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4362. Min Act: -0.0000

Data Index: 596286 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1942067 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4461. Min Act: -0.0000

Data Index: 471075 (The Pile)

Max Activating Token Index: 599